United States

Most video anomaly detection methods discriminate events that deviate from normal patterns as anomalies. However, these methods are prone to interferences from event-irrelevant factors,  such as background textures and object scale variations,  incurring an increased false detection rate. In this paper, we propose to explicitly learn event-relevant factors to eliminate the interferences from event-irrelevant factors on anomaly predictions.  To this end, we introduce a causal generative model to separate the event-relevant factors and event-irrelevant ones in videos, and learn the prototypes of event-relevant factors in a memory augmentation module.   We design a causal objective function to optimize the causal generative model and develop a counterfactual learning strategy to guide anomaly predictions, which increases the influence of the event-relevant factors. The extensive experiments show the effectiveness of our method for video anomaly detection.

AAAI 2023

Learning Event-Relevant Factors for Video Anomaly Detection

video understanding & activity analysis

causal learning

applications

machine learning

computer vision

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-23 is the Thirty-Seventh AAAI Conference on Artificial Intelligence. The theme of this conference is to create collaborative bridges within and beyond AI. Like previous AAAI conferences, AAAI-23 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and two new activities: a Bridge Program and a Lab Program. Many of these activities are tailored to the theme of bridges and all are selected according to the highest standards, with additional programs for students and young researchers. 
AAAI is providing you with a conference planner, which you can use to help organize your itinerary of activities. This includes talks to attend in person, talks to attend remotely, breaks with colleagues and your site seeing activities. To access this conference planner, please go to [https://aaai-2023.takemobi.io](https://aaai-2023.takemobi.io).

In order to access this site, you need to register. If you haven't already, please register [here](https://aaai.org/Conferences/AAAI-23/registration/).


The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines.

poster

Multi-scale features from backbone networks have been widely applied to recover object details in segmentation tasks. Generally, the multi-level features are fused in a certain manner for further pixel-level dense prediction. Whereas, the spatial structure information is not fully explored, that is similar nearby pixels can be used to complement each other. In this paper, we investigate a progressive neighborhood aggregation (PNA) framework to refine the semantic segmentation prediction, resulting in an end-to-end solution that can perform the coarse prediction and refinement in a unified network. Specifically, we first present a neighborhood aggregation module, the neighborhood similarity matrices for each pixel are estimated on multi-scale features, which are further used to progressively aggregate the high-level feature for recovering the spatial structure. In addition, to further integrate the high-resolution details into the aggregated feature, we apply a self-aggregation module on the low-level features to emphasize important semantic information for complementing losing spatial details. Extensive experiments on five segmentation datasets, including Pascal VOC 2012, CityScapes, COCO-Stuff 10k, DeepGlobe, and Trans10k, demonstrate that the proposed framework can be cascaded into existing segmentation models providing consistent improvements. In particular, our method achieves new state-of-the-art performances on two challenging datasets, DeepGlobe and Trans10k. The code is available at https://github.com/liutinglt/PNA.

Progressive Neighborhood Aggregation for Semantic Segmentation Refinement

The Traveling Tournament Problem (TTP-$k$) is a well-known benchmark problem in tournament timetabling and has been extensively studied in the field of AI. In this problem, we are going to design a double round-robin schedule such that each pair of teams plays one game in each other's home venue, minimizing the total distance traveled by all $n$ teams ($n$ is even) under the constraint that each team can have at most $k$-consecutive home games or away games. The Linear Distance Traveling Tournament Problem (LDTTP-$k$), where all teams are located on a line, was introduced by Hoshino and Kawarabayashi (AAAI 2012). For LDTTP-3, they gave a $4/3$-approximation algorithm for $n\equiv4\pmod6$ teams. In this paper, We show that for any $3\leq k=o(\sqrt[3]{n})$, LDTTP-$k$ allows an efficient polynomial-time approximation scheme (EPTAS).

The Linear Distance Traveling Tournament Problem Allows an EPTAS

Automatic polyp segmentation from colonoscopy images is an essential prerequisite for the development of computer-assisted therapy. However, the complex semantic information and the blurred edges of polyps make segmentation extremely difficult. In this paper, we propose a novel semi-supervised polyp segmentation framework using affinity contrastive learning (ACL-Net), which is implemented between student and teacher networks to consistently refine the pseudo-labels for semi-supervised polyp segmentation. By aligning the affinity maps between the two branches, a better polyp region activation can be obtained to fully exploit the appearance-level context encoded in the feature maps, thereby improving the capability of capturing not only global localization and shape context, but also the local textural and boundary details. By utilizing the rich inter-image affinity context and establishing a global affinity context based on the memory bank, a cross-image affinity aggregation (CAA) module is also implemented to further refine the affinity aggregation between the two branches. By continuously and adaptively refining pseudo-labels with optimized affinity, we can improve the semi-supervised polyp segmentation based on the mutually reinforced knowledge interaction among contrastive learning and consistency learning iterations. Extensive experiments on five benchmark datasets, including Kvasir-SEG, CVC-ClinicDB, CVC-300, CVC-ColonDB and ETIS, demonstrate the effectiveness and superiority of our method. Codes are available at https://github.com/xiewende/ACL-Net.

ACL-Net: Semi-supervised Polyp Segmentation via Affinity Contrastive Learning

Spatial and temporal modeling is one of the most core aspects of few-shot action recognition. Most previous works mainly focus on long-term temporal relation modeling based on high-level spatial representations, without considering the crucial low-level spatial features and short-term temporal relations. Actually, the former feature could bring rich local semantic information, and the latter feature could represent motion characteristics of adjacent frames, respectively. In this paper, we propose SloshNet, a new framework that revisits the spatial and temporal modeling for few-shot action recognition in a finer manner. First, to exploit the low-level spatial features, we design a feature fusion architecture search module to automatically search for the best combination of the low-level and high-level spatial features. Next, inspired by the recent transformer, we introduce a long-term temporal modeling module to model the global temporal relations based on the extracted spatial appearance features. Meanwhile, we design another short-term temporal modeling module to encode the motion characteristics between adjacent frame representations. After that, the final predictions can be obtained by feeding the embedded rich spatial-temporal features to a common frame-level class prototype matcher. We extensively validate the proposed SloshNet on four few-shot action recognition datasets, including Something-Something V2, Kinetics, UCF101, and HMDB51. It achieves favorable results against state-of-the-art methods in all datasets.

Revisiting the Spatial and Temporal Modeling for Few-shot Action Recognition

Belief propagation is a widely used incomplete optimization algorithm, whose main theoretical properties hold only under the assumptions that beliefs are not equal. Nevertheless, there is much evidence that equality between beliefs does occur. A method to overcome belief equality by using unary function-nodes is assumed to resolve the problem.

We focus on Min-sum, the belief propagation version for solving constraint optimization problems. We prove that on a single cycle graph, belief equality can be avoided only when the algorithm converges to the optimal solution. In any other case, the unary function methods will not prevent equality, rendering some existing results in need of reassessment. We differentiate between belief equality, which includes equal beliefs in a single message, and assignment equality, that prevents a coherent selection of assignments to variables. We show the necessary and satisfying conditions for both. 

Separate but equal: Equality in Belief Propagation for Single Cycle Graphs

Event causality identification (ECI) aims to identify the
causal relationship between events, which plays a crucial role
in deep text understanding. Due to the diversity of real-world
causality events and difficulty in obtaining sufficient training
data, existing ECI approaches have poor generalizability and
struggle to identify the relation between seldom seen events.
In this paper, we propose to utilize both external knowledge
and internal analogy to improve ECI. On the one hand, we
utilize a commonsense knowledge graph called ConceptNet
to enrich the description of an event sample and reveal the
commonalities or associations between different events. On
the other hand, we retrieve similar events as analogy exam-
ples and glean useful experiences from such analogous neigh-
bors to better identify the relationship between a new event
pair. By better understanding different events through exter-
nal knowledge and making an analogy with similar events, we
can alleviate the data sparsity issue and improve model gener-
alizability. Extensive evaluations on two benchmark datasets
show that our model outperforms other baseline methods by
around 18% on the F1-value on average

Identify Event Causality with Knowledge and Analogy

Video-Text pre-training aims at learning transferable representations from large-scale video-text pairs via aligning the semantics between visual and textual information. State-of-the-art approaches extract visual features from raw pixels in an end-to-end fashion. However, these methods operate at frame-level directly and thus overlook the spatio-temporal structure of objects in video, which yet has a strong synergy with nouns in textual descriptions. In this work, we propose a simple yet effective module for video-text representation learning, namely RegionLearner, which can take into account the structure of objects during pre-training on large-scale video-text pairs. Given a video, our module (1) first quantizes continuous visual features via clustering patch-features into the same cluster according to content similarity, then (2) generates learnable masks to aggregate fragmentary the features into regions with complete semantics, and finally (3) models the spatio-temporal dependencies between different semantic regions. In contrast to using off-the-shelf object detectors, our proposed module does not require explicit supervision and is much more computationally efficient. We pre-train the proposed approach on the public WebVid2M and CC3M datasets. Extensive evaluations on four downstream video-text retrieval benchmarks clearly demonstrate the effectiveness of our RegionLearner. 

Video-Text Pre-training with Learned Regions for Retrieval

Recent advancement of large-scale pretrained models such as BERT, GPT-3, CLIP, and Gopher, has shown astonishing achievements across various task domains. Unlike vision recognition and language models, studies on general-purpose user representation at scale still remain underexplored. Here we explore the possibility of general-purpose user representation learning by training a universal user encoder at large scales. We demonstrate that the scaling law is present in user representation learning areas, where the training error scales as a power-law with the amount of computation. Our Contrastive Learning User Encoder (CLUE), optimizes task-agnostic objectives, and the resulting user embeddings stretch our expectation of what is possible to do in various downstream tasks. CLUE also shows great transferability to other domains and companies, as performances on an online experiment shows significant improvements in Click-Through-Rate (CTR).  Furthermore, we also investigate how the model performance is influenced by the scale factors, such as training data size, model capacity, sequence length, and batch size. Finally, we discuss the broader impacts of CLUE in general. 

Scaling Law for Recommendation Models: Towards General-purpose User Representations

Social reasoning necessitates the capacity of theory of mind (ToM), the ability to contextualise and attribute mental states to others without having access to their internal cognitive structure. Recent machine learning approaches to ToM have demonstrated that we can train the observer to read the past and present behaviours of other agents and infer their beliefs (including false beliefs about things that no longer exist), goals, intentions and future actions. The challenges arise when the behavioural space is complex, demanding skilful space navigation for rapidly changing contexts for an extended period. We tackle the challenges by equipping the observer with novel neural memory mechanisms to encode, and hierarchical attention to selectively retrieve information about others. The memories allow rapid, selective querying of distal related past behaviours of others to deliberatively reason about their current mental state, beliefs and future behaviours. This results in ToMMY, a theory of mind model that learns to reason while making little assumptions about the underlying mental processes. We also construct a new suite of experiments to demonstrate that memories facilitate the learning process and achieve better theory of mind performance, especially for high-demand false-belief tasks that require inferring through multiple steps of changes.

Memory-Augmented Theory of Mind Network

Adversarial attack on point clouds plays a vital role in evaluating and improving the adversarial robustness of 3D deep learning models. Current attack methods are mainly applied by point perturbation in a non-manifold manner. In this paper, we formulate a novel manifold attack, which deforms the underlying 2-manifold surfaces via parameter plane stretching to generate adversarial point clouds. First, we represent the mapping between the parameter plane and underlying surface using generative-based networks. Second, the stretching is learned in the 2D parameter domain such that the generated 3D point cloud fools a pretrained classifier with minimal geometric distortion. Extensive experiments show that adversarial point clouds generated by manifold attack are smooth, undefendable and transferable, and outperform those samples generated by the state-of-the-art non-manifold ones.

Learning Event-Relevant Factors for Video Anomaly Detection

Downloads

Next from AAAI 2023

Progressive Neighborhood Aggregation for Semantic Segmentation Refinement

Similar lecture

GradPU: Positive-Unlabeled Learning via Gradient Penalty and Positive Upweighting