Identifying common patterns among events is a key ability in human and machine perception, as it underlies intelligent decision making. We propose an approach for learning semantic relational set abstractions on videos, inspired by human learning. We combine visual features with natural language supervision to generate high-level representations of similarities across a set of videos. This allows our model to perform cognitive tasks such as set abstraction (which general concept is in common among a set of videos?), set completion (which new video goes well with the set?), and odd one out detection (which video does not belong to the set?). Experiments on two video benchmarks, Kinetics and Multi-Moments in Time, show that robust and versatile representations emerge when learning to recognize commonalities among sets. We compare our model to several baseline algorithms and show that significant improvements result from explicitly learning relational abstractions with semantic supervision.
Convolution has been arguably the most important feature transform for modern neural networks, leading to the advance of deep learning. Recent emergence of Transformer networks, which replace convolution layers with self-attention blocks, has revealed the limitation of stationary convolution kernels and opened the door to the era of dynamic feature transforms. The existing dynamic transforms, including self-attention, however, are all limited for video understanding where correspondence relations in space and time, i.e., motion information, are crucial for effective representation. In this wor…
The ability to predict future outcomes conditioned on observed video frames is crucial for intelligent decision-making in autonomous systems. Recently, deep recurrent architectures have been applied to the task of video prediction. However, this often results in blurry predictions and requires tedious training on large datasets. Here, we explore a different approach by (1) using frequency-domain approaches for video prediction and (2) explicitly inferring object-motion relationships in the observed scene. The resulting predictions are consistent with the observed dynamics in a scene and do not…
Humans frequently use referring (identifying) expressions to refer to objects. Especially in ambiguous settings, humans prefer expressions (called relational referring expressions) that describe an object with respect to a distinguishing, unique object. Unlike studies on video object search using referring expressions, in this paper, our focus is on (i) relational referring expressions in highly ambiguous settings, and (ii) methods that can both generate and comprehend a referring expression. For this goal, we first introduce a new dataset for video object search with referring expressions tha…
Temporal relational reasoning, the ability to link meaningful transformations of objects or entities over time, is a fundamental property of intelligent species. In this paper, we introduce an effective and interpretable network module, the Temporal Relation Network (TRN), designed to learn and reason about temporal dependencies between video frames at multiple time scales. We evaluate TRN-equipped networks on activity recognition tasks using three recent video datasets - Something-Something, Jester, and Charades - which fundamentally depend on temporal relational reasoning. Our results demons…
Spatial and temporal relationships, both short-range and long-range, between objects in videos, are key cues for recognizing actions. It is a challenging problem to model them jointly. In this paper, we first present a new variant of Long Short-Term Memory, namely Relational LSTM, to address the challenge of relation reasoning across space and time between objects. In our Relational LSTM module, we utilize a non-local operation similar in spirit to the recently proposed non-local network to substitute the fully connected operation in the vanilla LSTM. By doing this, our Relational LSTM is capa…
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；UiT The Arctic University of Norway（挪威北极大学）；Carnegie Mellon University（卡内基梅隆大学）；Xidian University（西安电子科技大学）
The large amount of videos popping up every day, make it more and more critical that key information within videos can be extracted and understood in a very short time. Video summarization, the task of finding the smallest subset of frames, which still conveys the whole story of a given video, is thus of great significance to improve efficiency of video understanding. We propose a novel Dilated Temporal Relational Generative Adversarial Network (DTR-GAN) to achieve frame-level video summarization. Given a video, it selects the set of key frames, which contain the most meaningful and compact in…
University of Surrey（萨里大学）；National Institute of Technology（国家理工学院）
Video activity recognition by deep neural networks is impressive for many classes. However, it falls short of human performance, especially for challenging to discriminate activities. Humans differentiate these complex activities by recognising critical spatio-temporal relations among explicitly recognised objects and parts, for example, an object entering the aperture of a container. Deep neural networks can struggle to learn such critical relationships effectively. Therefore we propose a more human-like approach to activity recognition, which interprets a video in sequential temporal phases …
We propose a novel approach to few-shot action recognition, finding temporally-corresponding frame tuples between the query and videos in the support set. Distinct from previous few-shot works, we construct class prototypes using the CrossTransformer attention mechanism to observe relevant sub-sequences of all support videos, rather than using class averages or single best matches. Video representations are formed from ordered tuples of varying numbers of frames, which allows sub-sequences of actions at different speeds and temporal offsets to be compared. Our proposed Temporal-Relational Cros…
GHR-VQA: Graph-guided Hierarchical Relational Reasoning for Video Question Answering
School of ECE National Technical University of Athens（国家技术大学雅典电子工程学院）；Robotics Institute Athena Research Center（雅典研究中心机器人研究所）；University of Luxembourg（卢森堡大学）
Center for Research on Intelligent Perception and Computing（智能感知与计算研究中心）；National Laboratory of Pattern Recognition（模式识别国家重点实验室）；Center for Excellence in Brain Science and Intelligence Technology（脑科学与智能技术卓越创新中心）；Institute of Automation Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Recently, pose-based action recognition has gained more and more attention due to the better performance compared with traditional appearance-based methods. However, there still exist two problems to be further solved. First, existing pose-based methods generally recognize human actions with captured 3D human poses which are very difficult to obtain in real scenarios. Second, few pose-based methods model the action-related objects in recognizing human-object interaction actions in which objects play an important role. To solve the problems above, we propose a pose-based two-stream relational n…
University of Perugia（佩鲁贾大学）；Institut de Robòtica i Informàtica Industrial (CSIC-UPC)（机器人与工业信息研究所（西班牙国家研究委员会-加泰罗尼亚理工大学））
In this paper we propose a new framework to categorize social interactions in egocentric videos, we named InteractionGCN. Our method extracts patterns of relational and non-relational cues at the frame level and uses them to build a relational graph from which the interactional context at the frame level is estimated via a Graph Convolutional Network based approach. Then it propagates this context over time, together with first-person motion information, through a Gated Recurrent Unit architecture. Ablation studies and experimental evaluation on two publicly available datasets validate the pro…
Beijing Institute of Technology（北京理工大学）；University of Rochester（罗切斯特大学）
Exploiting relationships among objects has achieved remarkable progress in interpreting images or videos by natural language. Most existing methods resort to first detecting objects and their relationships, and then generating textual descriptions, which heavily depends on pre-trained detectors and leads to performance drop when facing problems of heavy occlusion, tiny-size objects and long-tail in object detection. In addition, the separate procedure of detecting and captioning results in semantic inconsistency between the pre-defined object/relation categories and the target lexical words. W…
Duke University（杜克大学）；NEC Laboratories America（NEC美国实验室）
Previous models for video captioning often use the output from a specific layer of a Convolutional Neural Network (CNN) as video features. However, the variable context-dependent semantics in the video may make it more appropriate to adaptively select features from the multiple CNN layers. We propose a new approach for generating adaptive spatiotemporal representations of videos for the captioning task. A novel attention mechanism is developed, that adaptively and sequentially focuses on different layers of CNN features (levels of feature "abstraction"), as well as local spatiotemporal regions…
VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models
Dept. of CSE & School of AI & MoE Key Lab of Al, Shanghai Jiao Tong University（计算机科学与工程系及人工智能学院及人工智能基础实验室，上海交通大学）；Shanghai Jiao Tong University（上海交通大学）；The Chinese University of Hong Kong（香港中文大学）
TRCoRSurg: Temporal-Relational Co-Reasoning for Surgical Video Triplet Recognition
Beihang University（北京航空航天大学）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Shenzhen University of Advanced Technology（深圳理工大学）
Adaptive Dense Evidence Refinement for Video Relational Reasoning for VRR-QA Challenge
Southeast University（东南大学）；National University of Singapore（国立新加坡大学）；Independent Researcher（独立研究员）；Opus AI Research（Opus AI研究）；University of Science and Technology of China（中国科学技术大学）
Towards Robust Referring Video Object Segmentation with Cyclic Relational Consensus
Carnegie Mellon University（卡内基梅隆大学）；Microsoft Research Asia（微软亚洲研究院）；University of Michigan（密歇根大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）
Temporal relational modeling in video is essential for human action understanding, such as action recognition and action segmentation. Although Graph Convolution Networks (GCNs) have shown promising advantages in relation reasoning on many tasks, it is still a challenge to apply graph convolution networks on long video sequences effectively. The main reason is that large number of nodes (i.e., video frames) makes GCNs hard to capture and model temporal relations in videos. To tackle this problem, in this paper, we introduce an effective GCN module, Dilated Temporal Graph Reasoning Module (DTGR…
Zhejiang University（浙江大学）；University of California, Santa Cruz（加利福尼亚大学圣克鲁兹分校）；University of California, Santa Barbara（加利福尼亚大学圣巴巴拉分校）
Grounded video description (GVD) encourages captioning models to attend to appropriate video regions (e.g., objects) dynamically and generate a description. Such a setting can help explain the decisions of captioning models and prevents the model from hallucinating object words in its description. However, such design mainly focuses on object word generation and thus may ignore fine-grained information and suffer from missing visual concepts. Moreover, relational words (e.g., "jump left or right") are usual spatio-temporal inference results, i.e., these words cannot be grounded on certain spat…
National Laboratory of Pattern Recognition, CASIA（中国科学院自动化研究所模式识别国家重点实验室）；University of Chinese Academy of Sciences（中国科学院大学）；University of Science and Technology of China（中国科学技术大学）；PeopleAI, Inc.（人民人工智能有限公司）；State Key Laboratory of Communication Content Cognition, People’s Daily Online（人民网传播内容认知国家重点实验室）；Aerospace Information Research Institute, CAS（中国科学院空天信息创新研究院）；Center for Excellence in Brain Science and Intelligence Technology, CAS（中国科学院脑科学与智能技术卓越创新中心）
Taking full advantage of the information from both vision and language is critical for the video captioning task. Existing models lack adequate visual representation due to the neglect of interaction between object, and sufficient training for content-related words due to long-tailed problems. In this paper, we propose a complete video captioning system including both a novel model and an effective training strategy. Specifically, we propose an object relational graph (ORG) based encoder, which captures more detailed interaction features to enrich visual representation. Meanwhile, we design a …
University of Surrey（萨里大学）；University of Edinburgh（爱丁堡大学）
Automatic data abstraction is an important capability for both benchmarking machine intelligence and supporting summarization applications. In the former one asks whether a machine can `understand' enough about the meaning of input data to produce a meaningful but more compact abstraction. In the latter this capability is exploited for saving space or human time by summarizing the essence of input data. In this paper we study a general reinforcement learning based framework for learning to abstract sequential data in a goal-driven way. The ability to define different abstraction goals uniquely…
University of California Los Angeles（加州大学洛杉矶分校）；University College London（伦敦大学学院）；USC Information Sciences Institute（南加州大学信息科学研究所）；Imperial College London（帝国理工学院）；U.S. Army Research Laboratory（美国陆军研究实验室）；U.S. Air Force Research Lab（美国空军研究实验室）
Recent efforts in interpretable deep learning models have shown that concept-based explanation methods achieve competitive accuracy with standard end-to-end models and enable reasoning and intervention about extracted high-level visual concepts from images, e.g., identifying the wing color and beak length for bird-species classification. However, these concept bottleneck models rely on a necessary and sufficient set of predefined concepts-which is intractable for complex tasks such as video classification. For complex tasks, the labels and the relationship between visual elements span many fra…
NOUS: Video-Driven 3D Human Reaction Generation via Observation-Reaction Mutual Steering
Nanyang Technological University（南洋理工大学）；National University of Singapore（新加坡国立大学）；Renmin University of China（中国人民大学）；University of Science and Technology of China（中国科学技术大学）；Hefei University of Technology（合肥工业大学）
We propose a deep semantic characterization of space and motion categorically from the viewpoint of grounding embodied human-object interactions. Our key focus is on an ontological model that would be adept to formalisation from the viewpoint of commonsense knowledge representation, relational learning, and qualitative reasoning about space and motion in cognitive robotics settings. We demonstrate key aspects of the space & motion ontology and its formalization as a representational framework in the backdrop of select examples from a dataset of everyday activities. Furthermore, focussing on hu…
Applied Artificial Intelligence Institute, Deakin University（迪肯大学应用人工智能学院）
Human activities are naturally structured as hierarchies unrolled over time. For action prediction, temporal relations in event sequences are widely exploited by current methods while their semantic coherence across different levels of abstraction has not been well explored. In this work we model the hierarchical structure of human activities in videos and demonstrate the power of such structure in action prediction. We propose Hierarchical Encoder-Refresher-Anticipator, a multi-level neural machine that can learn the structure of human activities by observing a partial hierarchy of events and…
In this paper, we present a method to estimate a sequence of human poses in unconstrained videos. We aim to demonstrate that by using temporal information, the human pose estimation results can be improved over image based pose estimation methods. In contrast to the commonly employed graph optimization formulation, which is NP-hard and needs approximate solutions, we formulate this problem into a unified two stage tree-based optimization problem for which an efficient and exact solution exists. Although the proposed method finds an exact solution, it does not sacrifice the ability to model the…
Why Relational Graphs Will Save the Next Generation of Vision Foundation Models?
Department of Computer Science, School of Mathematics, Statistics and Computer Science, College of Science, University of Tehran, Tehran, Iran（塔里斯坦大学科学学院计算机科学系）
Automating the analysis of imagery of the Gastrointestinal (GI) tract captured during endoscopy procedures has substantial potential benefits for patients, as it can provide diagnostic support to medical practitioners and reduce mistakes via human error. To further the development of such methods, we propose a two-stream model for endoscopic image analysis. Our model fuses two streams of deep feature inputs by mapping their inherent relations through a novel relational network model, to better model symptoms and classify the image. In contrast to handcrafted feature-based models, our proposed …
UC Berkeley（加州大学伯克利分校）；Facebook AI Research（Facebook人工智能研究院）；UIUC（伊利诺伊大学厄巴纳-香槟分校）
Planning at a higher level of abstraction instead of low level torques improves the sample efficiency in reinforcement learning, and computational efficiency in classical planning. We propose a method to learn such hierarchical abstractions, or subroutines from egocentric video data of experts performing tasks. We learn a self-supervised inverse model on small amounts of random interaction data to pseudo-label the expert egocentric videos with agent actions. Visuomotor subroutines are acquired from these pseudo-labeled videos by learning a latent intent-conditioned policy that predicts the inf…
MovieTeller: Tool-augmented Movie Synopsis with ID Consistent Progressive Abstraction
Central Universities（中央高校）；National Natural Science Foundation of China（中国国家自然科学基金委员会）；Research Fund for International Scientists of National Natural Science Foundation of China（中国国家自然科学基金委员会国际科学家研究基金）
In e-commerce, consumer-generated videos, which in general deliver consumers' individual preferences for the different aspects of certain products, are massive in volume. To recommend these videos to potential consumers more effectively, diverse and catchy video titles are critical. However, consumer-generated videos seldom accompany appropriate titles. To bridge this gap, we integrate comprehensive sources of information, including the content of consumer-generated videos, the narrative comment sentences supplied by consumers, and the product attributes, in an end-to-end modeling framework. A…
University of Freiburg（弗莱堡大学）；Toyota Research Institute（丰田研究院）
Robots coexisting with humans in their environment and performing services for them need the ability to interact with them. One particular requirement for such robots is that they are able to understand spatial relations and can place objects in accordance with the spatial relations expressed by their user. In this work, we present a convolutional neural network for estimating pixelwise object placement probabilities for a set of spatial relations from a single input image. During training, our network receives the learning signal by classifying hallucinated high-level scene representations as…
