Papers

Grounded Situation Recognition (GSR), i.e., recognizing the salient activity (or verb) category in an image (e.g.,buying) and detecting all corresponding semantic roles (e.g.,agent and goods), is an essential step towards “human-like” event understanding. Since each verb is associated with a specific set of semantic roles, all existing GSR methods resort to a two-stage framework: predicting the verb in the first stage and detecting the semantic roles in the second stage. However, there are obvious drawbacks in both stages: 1) The widely-used cross-entropy (XE) loss for object recognition is insufficient in verb classification due to the large intra-class variation and high inter-class similarity among daily activities. 2) All semantic roles are detected in an autoregressive manner, which fails to model the complex semantic relations between different roles. To this end, we propose a novel SituFormerfor GSR which consists of a Coarse-to-Fine Verb Model (CFVM) and a Transformer-based Noun Model (TNM). CFVM is a two-step verb prediction model: a coarse-grained model trained with XE loss first proposes a set of verb candidates, and then a fine-grained model trained with triplet loss re-ranks these candidates with enhanced verb features (not only separable but also discriminative). TNM is a transformer-based semantic role detection model, which detects all roles parallelly. Owing to the global relation modeling ability and flexibility of the transformer decoder, TNM can fully explore the statistical dependency of the roles. Extensive validations on the challenging SWiG benchmark show that SituFormer achieves a new state-of-the-art performance with significant gains under various metrics. Code is available at https://github.com/kellyiss/SituFormer.

poster session 1 @ blue 4, poster session 11 @ blue 4, poster session 1, poster session 11

Omnidirectional images, also called 360 degree images, have attracted extensive attention in recent years, due to the rapid development of virtual reality (VR) technology. During omnidirectional image processing, including capture, transmission, consumption, and \emph{etc}, measuring the perceptual quality of omnidirectional images is highly necessary, since it plays a great role in guaranteeing the immersive quality of experience (IQoE). In this paper, we conduct a comprehensive study on perceptual quality of omnidirectional images from both subjective and objective perspectives. Specifically, we construct the largest so far subjective omnidirectional image quality database, where we consider several key influential elements, i.e., realistic non-uniform distortion, viewing condition, and viewing behavior, from the user view. In addition to subjective quality scores, we also record head and eye movement data. Besides, we make the first attempt by using the proposed database to train a convolutional neural network (CNN) for blind omnidirectional image quality assessment. To be consistent with the human viewing behavior in the VR device, we extract viewports from each omnidirectional image by using user viewing behaviors and obtain several video representations under different viewing conditions which are adopted as inputs of the proposed model. The proposed model is composed of two parts, including a multi-scale CNN-based feature extraction module and a perceptual quality prediction module. The feature extraction module is used to incorporate the multi-scale features, and the perceptual quality prediction module regresses them to perceived quality scores. The experimental results on our database verify that the proposed model achieves the competing performance compared with the state-of-the-art methods.

poster session 1 @ blue 4, poster session 11 @ blue 4, oral session 11 @ blue 4, poster session 1, poster session 11, oral session 11

There have been two streams in the 3D detection from point clouds: single-stage methods and two-stage methods. While the former is more computationally efficient, the latter usually provides better detection accuracy. By carefully examining the two-stage approaches, we have found that if appropriately designed, the first stage can produce accurate box regression. In this scenario, the second stage mainly rescores the boxes such that the boxes with better localization get selected. From this observation, we have devised a single-stage anchor-free network that can fulfill these requirements. This network, named AFDetV2, extends the previous work by incorporating a self-calibrated convolution block in the backbone, a keypoint auxiliary supervision, and an IoU prediction branch in the multi-task head. We take a simple product of the predicted IoU score with the classification heatmap to form the final classification confidence. The enhanced backbone strengthens the box localization capability, and the rescoring approach effectively joins the object presence confidence and the box regression accuracy. As a result, the detection accuracy is drastically boosted in the single-stage. To evaluate our approach, we have conducted extensive experiments on the Waymo Open Dataset and the nuScenes Dataset. We have observed that our AFDetV2 achieves the state-of-the-art results on these two datasets, superior to all the prior arts, including both the single-stage and the two-stage 3D detectors. AFDetV2 won the 1st place in the Real-Time 3D Detection of the Waymo Open Dataset Challenge 2021. In addition, a variant of our model AFDetV2-Base was entitled the "Most Efficient Model" by the Challenge Sponsor, showing a superior computational efficiency. To demonstrate the generality of this single-stage method, we have also applied it to the first stage of the two-stage networks. Without exception, the results show that with the strengthened backbone and the rescoring approach, the second stage refinement is no longer needed.

poster session 1 @ blue 4, poster session 11 @ blue 4, poster session 1, poster session 11

In sequential decision making, objective specifications are often underspecified or incomplete, neglecting to take into account potential (negative) side effects. Executing plans without consideration of their side effects can lead to catastrophic outcomes -- a concern recently raised in relation to the safety of AI. In this paper we investigate how to avoid side effects in a symbolic planning setting. We study the notion of minimizing side effects in the context of a planning environment where multiple independent agents co-exist. We define (classes of) negative side effects in terms of their effect on the agency of those other agents. Finally, we show how plans which minimize side effects of different types can be computed via compilations to cost-optimizing symbolic planning, and investigate experimentally.

poster session 1 @ blue 4, poster session 11 @ blue 4, poster session 1, poster session 11

Event camera has offered promising alternative for visual perception, especially in high speed and high dynamic range scenes. Recently, many deep learning methods have shown great success in providing model-free solutions to many event-based problems, such as optical flow estimation. However, existing deep learning methods did not address the importance of temporal information well from the perspective of architecture design and cannot effectively extract spatio-temporal features. Another line of research that utilizes Spiking Neural Network suffers from training issues for deeper architecture. To address these points, a novel input representation is proposed that captures the events temporal distribution for signal enhancement. Moreover, we introduce a spatio-temporal recurrent encoding-decoding neural network architecture for event-based optical flow estimation, which utilizes Convolutional Gated Recurrent Units to extract feature maps from a series of event images. Besides, our architecture allows some traditional frame-based core modules, such as correlation layer and iterative residual refine scheme, to be incorporated. The network is end-to-end trained with self-supervised learning on the Multi-Vehicle Stereo Event Camera dataset. We have shown that it outperforms all the existing state-of-the-art methods by a large margin.

poster session 1 @ blue 4, poster session 11 @ blue 4, poster session 1, poster session 11

Person re-identification (Re-ID) based on unsupervised domain adaptation (UDA) aims to transfer the pre-trained model from one labeled source domain to an unlabeled target domain. Existing methods tackle this problem by using clustering methods to generate pseudo labels. However, pseudo labels produced by these techniques may be unstable and noisy, substantially deteriorating models' performance. In this paper, we propose a Reliability Exploration with Self-ensemble Learning (RESL) framework for domain adaptive person Re-ID. First, to increase the feature diversity, multiple branches are presented to extract features from different data augmentations. Taking the temporally average model as a mean teacher model, online label refining is conducted by using its dynamic ensemble predictions from different branches as soft labels. Second, to combat the adverse effects of unreliable samples in clusters, sample reliability is estimated by evaluating the consistency of different clusters’ results, followed by selecting reliable instances for training and re-weighting sample contribution within Re-ID losses. A contrastive loss is also utilized with cluster-level memory features which are updated by the mean feature. The experiments demonstrate that our method can significantly surpass the state-of-the-art performance on the unsupervised domain adaptive person Re-ID.

poster session 1 @ blue 4, poster session 11 @ blue 4, poster session 1, poster session 11

Video moment localization aims at localizing the video segments which are most related to the given free-form natural language query. The weakly supervised setting, where only video level description is available during training, is getting more and more attention due to its lower annotation cost. Prior weakly supervised methods mainly use sliding windows to generate temporal proposals, which are independent of video content and low quality, and train the model to distinguish matched video-query pairs and unmatched ones collected from different videos, while neglecting what the model needs is to distinguish the unaligned segments within the video. In this work, we propose a novel weakly supervised solution by introducing Contrastive Negative sample Mining (CNM). Specifically, we use a learnable Gaussian mask to generate positive samples, highlighting the video frames most related to the query, and consider other frames of the video and the whole video as easy and hard negative samples respectively. We then train our network with the Intra-Video Contrastive loss to make our positive and negative samples more discriminative. Our method has two advantages: (1) Our proposal generation process with a learnable Gaussian mask is more efficient and makes our positive sample higher quality. (2) The more difficult intra-video negative samples enable our model to distinguish highly confusing scenes. Experiments on two datasets show the effectiveness of our method. Code can be found at https://github.com/minghangz/cnm.

poster session 1 @ blue 4, poster session 11 @ blue 4, poster session 1, poster session 11

Goal recognition design (GRD) is the task of modifying environments for aiding observers to recognize the objectives of agents during online observations. The worst case distinctiveness (WCD), a widely used performance measure in GRD research, can fail to provide useful guidance to the redesign process when some goals are too hard to be distinguished. Moreover, the existing WCD-based approaches do not work when an agent aims for a sequence of goals instead of just one goal. The paper presents a new GRD framework called extended goal recognition design (EGRD) for goal recognition that involves multiple goals. The objective of EGRD is to modify an environment to minimize the worst case distinctiveness of a goal condition that describes how an agent can reach a set of goals. A goal condition can be formally expressed in first-order computation tree logic (FO-CTL) that can be evaluated by model checking. We introduce a novel graphical representation of FO-CTL sentences that is suitable for extended goal recognition. Moreover, we present a search algorithm for EGRD with a novel caching mechanism. Our experimental results show that the caching mechanism can greatly speed up our EGRD search algorithm by reusing the previous evaluation of FO-CTL sentences.

poster session 1 @ blue 4, poster session 11 @ blue 4, poster session 1, poster session 11

We consider the problem of learning models of stochastic environments for planning, assuming that the transitions on the various state factors are independent. We suppose we have example trajectories of policies for random problems executing in an unknown environment, and we would like to match the rate of success of those policies. We present a polynomial-time algorithm that, given a polynomial number of trajectories, produces a PPDDL model such that optimal policies under the PPDDL model will provably achieve a success rate at future goals that is almost as good or better than the policies that produced the training trajectories. Moreover, we also consider a variant of PPDDL in which there is uncertainty about the transition probabilities, specified by an interval for each factor that contains the respective true transition probabilities. We also give a polynomial-time algorithm that, when given the example trajectories, produces such an imprecise-PPDDL environment model and guarantees that with high probability, the true environment is indeed captured by the uncertain parameters, while also guaranteeing that the optimal bound on the success probability in this model is almost as good or better than the success rate of the policies that produced the training examples.

poster session 1 @ blue 4, poster session 11 @ blue 4, oral session 1 @ blue 4, poster session 1, poster session 11, oral session 1

In most video platforms, such as Youtube, Kwai, and TikTok, the played videos usually have undergone multiple video encodings such as hardware encoding by recording devices, software encoding by video editing apps, and single/multiple video transcoding by video application servers. Previous works in compressed video restoration typically assume the compression artifacts are caused by one-time encoding. Thus, the derived solution usually does not work very well in practice. In this paper, we propose a new method, temporal spatial auxiliary network (TSAN), for transcoded video restoration. Our method considers the unique traits between video encoding and transcoding, and we consider the initial shallow encoded videos as the intermediate labels to assist the network to conduct self-supervised attention training. In addition, we employ adjacent multi-frame information and propose the temporal deformable alignment and pyramidal spatial fusion for transcoded video restoration. The experimental results demonstrate that the performance of the proposed method is superior to that of the previous techniques. The code is available at https://github.com/icecherylXuli/TSAN.

poster session 1 @ blue 4, poster session 11 @ blue 4, poster session 1, poster session 11

Diverse planning is an important problem in automated planning with many real world applications. Recently, diverse planning has seen renewed interest, with work that defines a taxonomy of computational problems with respect to both plan quality and solution diversity. However, despite the recent advances in diverse planning, the variety of approaches and the number of available planners are still quite limited, even nonexistent for several computational problems. In this work, we aim to extend the portfolio of planners for various computational problems in diverse planning. To that end, we introduce a novel approach to finding solutions for three computational problems within diverse planning and present planners for these three problems. For one of these problems, our approach is the first one that is able to provide solutions to the problem. For another, we show that top-k and top quality planners can provide, albeit naive, solutions to the problem and we extend these planners to improve the diversity of the solution. Finally, for the third problem, we show that some existing diverse planners already provide solutions to that problem. We suggest another approach and empirically show it to compare favorably with these existing planners.

poster session 1 @ blue 4, poster session 11 @ blue 4, poster session 1, poster session 11

Temporal graphs naturally model graphs whose underlying topology changes over time. Recently, the problems Temporal Vertex Cover (or TVC) and Sliding-Window Temporal Vertex Cover (or $\Delta$-TVC for time-windows of a fixed-length $\Delta$) have been established as natural extensions of the classic Vertex Cover problem on static graphs with connections to areas such as surveillance in sensor networks. In this paper we initiate a systematic study of the complexity of TVC and $\Delta$-TVC on sparse graphs. Our main result shows that for every $\Delta\geq 2$, $\Delta$-TVC is NP-hard even when the underlying topology is described by a path or a cycle. This resolves an open problem from literature and shows a surprising contrast between $\Delta$-TVC and TVC for which we provide a polynomial-time algorithm in the same setting. To circumvent this hardness, we present a number of exact and approximation algorithms for temporal graphs whose underlying topologies are given by a path, that have bounded vertex degree in every time step, or that admit a small-sized temporal vertex cover.

poster session 1 @ blue 4, poster session 11 @ blue 4, poster session 1, poster session 11

In this paper, we generalize the recently studied stochastic matching problem to more accurately model a significant medical process, kidney exchange, and several other applications. Up until now the stochastic matching problem that has been studied was as follows: given a graph G= (V,E), each edge is included in the realized sub-graph of G independently with probability p_e, and the goal is to find a degree-bounded sub-graph Q of G that has an expected maximum matching that approximates the expected maximum matching of G. This model does not account for possibilities of vertex dropouts, which can be found in several applications, e.g. in kidney exchange when donors or patients opt out of the exchange process as well as in online freelancing and online dating when online profiles are found to be faked. Thus, we will study a more generalized model of stochastic matching in which vertices and edges are both realized independently with some probabilities p_v, p_e, respectively, which more accurately fits important applications than the previously studied model. We will discuss the first algorithms and analysis for this generalization of thestochastic matching model and prove that they achieve good approximation ratios. In particular, we show that the approximation factor of a natural algorithm for this problem is at least 0.6568 in unweighted graphs, and 1/2+ε in weighted graphs for some constant ε >0. We further improve our result for unweighted graphs to 2/3 using edge degree constrained subgraphs (EDCS).

poster session 1 @ blue 4, poster session 11 @ blue 4, poster session 1, poster session 11

A Simple Temporal Network with Uncertainty (STNU) includes real-valued variables, called time-points; binary difference constraints on those time-points; and contingent links that represent actions with uncertain durations. STNUs have been used for robot control, web-service composition, and business processes. The most important property of an STNU is called dynamic controllability (DC); and algorithms for checking this property are called DC-checking algorithms. The DC-checking algorithm for STNUs with the best worst-case time-complexity is the RUL¯ algorithm due to Cairo, Hunsberger and Rizzi. Its complexity is O(mn + k^2n + kn log n), where n is the number of time-points, m is the number of constraints (equivalently, the number of edges in the STNU graph), and k is the number of contingent links. It is expected that this worst-case complexity cannot be improved upon. However, this paper provides an improved algorithm, called RUL2021, that improves its performance in practice by an order of magnitude, as demonstrated by a thorough empirical evaluation.

poster session 1 @ blue 4, poster session 11 @ blue 4, poster session 1, poster session 11

Integer programs provide a powerful abstraction for representing a wide range of real-world scheduling problems. Despite their ability to model general scheduling problems, solving large-scale integer programs (IP) remains a computational challenge in practice. The incorporation of more complex objectives such as robustness to disruptions further exacerbates the computational challenge. We present NICE (Neural network IP Coefficient Extraction), a novel technique that combines reinforcement learning and integer programming to tackle the problem of robust scheduling. More specifically, NICE uses reinforcement learning to approximately represent complex objectives in an integer programming formulation. We use NICE to determine assignments of pilots to a flight crew schedule so as to reduce the impact of disruptions. We compare NICE with (1) a baseline integer programming formulation that produces a feasible crew schedule, and (2) a robust integer programming formulation that explicitly tries to minimize the impact of disruptions. Our experiments show that, across a variety of scenarios, NICE produces schedules resulting in 33% to 48% fewer disruptions than the baseline formulation. Moreover, in more severely constrained scheduling scenarios in which the robust integer program fails to produce a schedule within 90 minutes, NICE is able to build robust schedules in less than 2 seconds on average.

poster session 1 @ blue 4, poster session 11 @ blue 4, poster session 1, poster session 11

The problem of knowledge-based visual question answering involves answering questions that require external knowledge in addition to the content of the image. Such knowledge typically comes in a variety of forms, including visual, textual, and commonsense knowledge. The use of more knowledge sources, however, also increases the chance of retrieving more irrelevant or noisy facts, making it difficult to comprehend the facts and find the answer. To address this challenge, we propose Multi-modal Answer Validation using External knowledge (MAVEx), where the idea is to validate a set of promising answer candidates based on answer-specific knowledge retrieval. This is in contrast to existing approaches that search for the answer in a vast collection of often irrelevant facts. Our approach aims to learn which knowledge source should be trusted for each answer candidate and how to validate the candidate using that source. We consider a multi-modal setting, relying on both textual and visual knowledge resources, including images searched using Google, sentences from Wikipedia articles, and concepts from ConceptNet. Our experiments with OK-VQA, a challenging knowledge-based VQA dataset, demonstrate that \mavex achieves new state-of-the-art results.

poster session 1 @ blue 4, poster session 11 @ blue 4, oral session 11 @ blue 4, poster session 1, poster session 11, oral session 11

Interpretability is crucial to understand the inner workings of deep neural networks (DNNs). Many interpretation methods help to understand the decision-making of DNNs by generating saliency maps that highlight parts of the input image that contribute the most to the prediction made by the DNN. In this paper we design a backdoor attack that alters the saliency map produced by the network for an input image with a specific trigger pattern while not losing the prediction performance significantly. The saliency maps are incorporated in the penalty term of the objective function that is used to train a deep model and its influence on model training is conditioned upon the presence of a trigger. We design two types of attacks: a targeted attack that enforces a specific modification of the saliency map and a non-targeted attack when the importance scores of the top pixels from the original saliency map are significantly reduced. We perform empirical evaluations of the proposed backdoor attacks on gradient-based interpretation methods, Grad-CAM and SimpleGrad, and a gradient-free scheme, VisualBackProp, for a variety of deep learning architectures. We show that our attacks constitute a serious security threat to the reliability of the interpretation methods when deploying models developed by untrusted sources. We furthermore show that existing backdoor defense mechanisms are ineffective in detecting our attacks. Finally, we demonstrate that the proposed methodology can be used in an inverted setting, where the correct saliency map can be obtained only in the presence of a trigger (key), effectively making the interpretation system available only to selected users.

poster session 1 @ blue 4, poster session 11 @ blue 4, poster session 1, poster session 11

We introduce a novel method for encoding cost optimal delete-free STRIPS Planning as SAT. Our method is based on representing any relaxed plan as a partial function from the set of propositions to the set of actions. This function can map any proposition to a unique action that adds the proposition during execution of the relaxed plan. We show that a relaxed plan can be produced by maintaining acyclicity in the graph of all causal relations among propositions, represented by the mentioned partial function. We also show that by efficient encoding of action cost propagation and enforcing a series of upper bounds on the total costs of the output plan, an optimal plan can effectively be produced for a given delete-free STRIPS problem. Our empirical results indicate that this method is quite competitive with the state-of-the-art, demonstrating a better coverage compared to that of competing methods on conventional STRIPS planning problems.

poster session 1 @ blue 4, poster session 11 @ blue 4, oral session 1 @ blue 4, poster session 1, poster session 11, oral session 1

Goal Recognition Design (GRD) problems identify the minimum number of environmental modifications aiming to force an interacting agent to reveal its goal as early as possible. Researchers proposed several extensions to the original model, some of them handling stochastic agent action outcomes. While this generalization is useful, it assumes optimal acting agents, which limits its applicability to more realistic scenarios. This paper presents the Suboptimal Stochastic GRD model, where we consider boundedly rational agents that, due to limited resources, might follow a suboptimal policy. Inspired by theories on human behavior asserting that humans are (close to) optimal when making perceptual decisions, we assume the chosen policy has at most m suboptimal actions. Our contribution includes (I) Extending the stochastic goal recognition design framework by supporting suboptimal agents in cases where an observer has either full or partial observability; (ii) Presenting methods to evaluate the ambiguity of the model under these assumptions; and (iii) Evaluating our approach on a range of benchmark applications.

poster session 1 @ blue 4, poster session 11 @ blue 4, poster session 1, poster session 11

Much of the research on learning symbolic models of AI agents focuses on agents with stationary models. This assumption fails to hold in settings where the agent’s capabilities may change as a result of learning, adaptation, or other post-deployment modifications. Efficient assessment of agents in such settings is critical for learning the true capabilities of an AI system and for ensuring its safe usage. In this work, we propose a novel approach to differentially assess black-box AI agents that have drifted from their prior known models. As a starting point, we consider the fully observable and deterministic setting. We leverage observations of the agent’s current behavior and knowledge of the initial model to generate an active querying policy that selectively queries the agent and computes an updated model of its functionality. Empirical evaluation shows that our approach is much more efficient than re-learning the agent model from scratch. We also show that the cost of differential assessment using our method is proportional to the amount of drift in the agent’s functionality.

poster session 1 @ blue 4, poster session 11 @ blue 4, oral session 1 @ blue 4, poster session 1, poster session 11, oral session 1

Oversubscription planning (OSP) is the problem of finding plans that maximize the utility value of their end state while staying within a specified cost bound. Recently, it has been shown that OSP problems can be reformulated as classical planning problems with multiple cost functions but no utilities. Here we take advantage of this reformulation to show that OSP problems can be solved optimally using the A* search algorithm, in contrast to previous approaches that have used variations on branch-and-bound search. This allows many powerful techniques developed for classical planning to be applied to OSP problems. We also introduce novel bound-sensitive heuristics, which are able to reason about the primary cost of a solution while taking into account secondary cost functions and bounds, to provide superior guidance compared to heuristics that do not take these bounds into account. We propose two such bound-sensitive variants of existing classical planning heuristics, and show experimentally that the resulting search is significantly more informed than with comparable heuristics that do not consider bounds.

poster session 1 @ blue 4, poster session 11 @ blue 4, poster session 1, poster session 11

Generalized zero-shot learning (GZSL) is a learning technique to identify unseen classes by exploiting attributes. In this paper, we propose a new GZSL technique exploiting attribute-related image features. While conventional GZSL approaches use image features containing attribute-irrelevant information for the classification, our approach, henceforth referred to as semantic feature extraction-based GZSL (SE-GZSL), exploits semantic features, features containing only attribute-related information, to remove the interference caused by attribute-irrelevant information. To extract semantic features, we introduce 1) mutual information (MI)-based loss to capture all the attribute-related information in the image features and 2) similarity-based loss to remove attribute-irrelevant information. From extensive experiments on various benchmark datasets, we show that SE-GZSL outperforms conventional GZSL techniques.

poster session 1 @ blue 4, poster session 11 @ blue 4, poster session 1, poster session 11

This work aims at improving instance retrieval with self-supervision. We find that fine-tuning using the recently developed self-supervised (SSL) learning methods, such as SimCLR and MoCo, fails to improve the performance of instance retrieval. In this work, we identify that the learnt representations for instance retrieval should be invariant to large variations in viewpoint and background etc., whereas self-augmented positives applied by the current SSL methods can not provide strong enough signals for learning robust instance-level representations. To overcome this problem, we propose InsCLR, a new SSL method that builds on the instance-level contrast, to learn the intra-class invariance by dynamically mining meaningful pseudo positive samples from both mini-batches and a memory bank during training. Extensive experiments demonstrate that InsCLR achieves similar or even better performance than the state-of-the-art SSL methods on instance retrieval. Code is available at https://github.com/zeludeng/insclr.

poster session 1 @ blue 4, poster session 11 @ blue 4, poster session 1, poster session 11

In this paper, we give a new definition for sample complexity, and further develop a theoretical analysis to bridge the gap between sample complexity and model capacity. In contrast to previous works which study on some toy samples, we conduct our analysis on more general data space, and build a qualitative relationship from sample complexity to model capacity required to achieve comparable performance. Besides, we introduce a simple indicator to evaluate the sample complexity based on continuous mapping. Moreover, we further analysis the relationship between sample complexity and data distribution, which paves the way to understand the present representation learning. Extensive experiments on several datasets well demonstrate the effectiveness of our evaluation method.

poster session 1 @ blue 4, poster session 11 @ blue 4, oral session 11 @ blue 4, poster session 1, poster session 11, oral session 11