In this work, we propose Knowledge Integration Networks (referred as KINet) for video action recognition. KINet is capable of aggregating meaningful context features which are of great importance to identifying an action, such as human information and scene context. We design a three-branch architecture consisting of a main branch for action recognition, and two auxiliary branches for human parsing and scene recognition which allow the model to encode the knowledge of human and scene for action recognition. We explore two pre-trained models as teacher networks to distill the knowledge of human and scene for training the auxiliary tasks of KINet. Furthermore, we propose a two-level knowledge encoding mechanism which contains a Cross Branch Integration (CBI) module for encoding the auxiliary knowledge into medium-level convolutional features, and an Action Knowledge Graph (AKG) for effectively fusing high-level context information. This results in an end-to-end trainable framework where the three tasks can be trained collaboratively, allowing the model to compute strong context knowledge efficiently. The proposed KINet achieves the state-of-the-art performance on a large-scale action recognition benchmark Kinetics-400, with a top-1 accuracy of 77.8%. We further demonstrate that our KINet has strong capability by transferring the Kinetics-trained model to UCF-101, where it obtains 97.8% top-1 accuracy.
University of Electronic Science and Technology of China（电子科技大学）；Beijing Aerospace Institute for Metrology and Measurement Technology（北京航天计量测试技术研究所）；Southwestern University of Finance and Economics（西南财经大学）
The recognition of behaviors in videos usually requires a combinatorial analysis of the spatial information about objects and their dynamic action information in the temporal dimension. Specifically, behavior recognition may even rely more on the modeling of temporal information containing short-range and long-range motions; this contrasts with computer vision tasks involving images that focus on the understanding of spatial information. However, current solutions fail to jointly and comprehensively analyze short-range motion between adjacent frames and long-range temporal aggregations at larg…
Facebook（脸书）；Zhejiang University（浙江大学）；MPI for Intelligent Systems（马克斯·普朗克智能系统研究所）；NVIDIA（英伟达）
Most of the top performing action recognition methods use optical flow as a "black box" input. Here we take a deeper look at the combination of flow and action recognition, and investigate why optical flow is helpful, what makes a flow method good for action recognition, and how we can make it better. In particular, we investigate the impact of different flow algorithms and input transformations to better understand how these affect a state-of-the-art action recognition method. Furthermore, we fine tune two neural-network flow methods end-to-end on the most widely used action recognition datas…
Most current action recognition methods heavily rely on appearance information by taking an RGB sequence of entire image regions as input. While being effective in exploiting contextual information around humans, e.g., human appearance and scene category, they are easily fooled by out-of-context action videos where the contexts do not exactly match with target actions. In contrast, pose-based methods, which take a sequence of human skeletons only as input, suffer from inaccurate pose estimation or ambiguity of human pose per se. Integrating these two approaches has turned out to be non-trivial…
SenseTime Research（商汤科技研究院）；Chongqing University（重庆大学）；Shanghai AI Laboratory（上海人工智能实验室）
Efficient spatiotemporal modeling is an important yet challenging problem for video action recognition. Existing state-of-the-art methods exploit neighboring feature differences to obtain motion clues for short-term temporal modeling with a simple convolution. However, only one local convolution is incapable of handling various kinds of actions because of the limited receptive field. Besides, action-irrelated noises brought by camera movement will also harm the quality of extracted motion features. In this paper, we propose a Temporal Saliency Integration (TSI) block, which mainly contains a S…
Shanghai Jiao Tong University（上海交通大学）；Nanjing University（南京大学）；University of Chinese Academy of Sciences（中国科学院大学）
Action recognition is an important yet challenging task in computer vision. In this paper, we propose a novel deep-based framework for action recognition, which improves the recognition accuracy by: 1) deriving more precise features for representing actions, and 2) reducing the asynchrony between different information streams. We first introduce a coarse-to-fine network which extracts shared deep features at different action class granularities and progressively integrates them to obtain a more accurate feature representation for input actions. We further introduce an asynchronous fusion netwo…
In this work, we address the problem how a network for action recognition that has been trained on a modality like RGB videos can be adapted to recognize actions for another modality like sequences of 3D human poses. To this end, we extract the knowledge of the trained teacher network for the source modality and transfer it to a small ensemble of student networks for the target modality. For the cross-modal knowledge distillation, we do not require any annotated data. Instead we use pairs of sequences of both modalities as supervision, which are straightforward to acquire. In contrast to previ…
University of Queensland（昆士兰大学）；Queensland University of Technology（昆士兰科技大学）；NICTA（澳大利亚国家信息通信技术中心）；Data61, CSIRO（澳大利亚联邦科学与工业研究组织 Data61）
We propose a hierarchical approach to multi-action recognition that performs joint classification and segmentation. A given video (containing several consecutive actions) is processed via a sequence of overlapping temporal windows. Each frame in a temporal window is represented through selective low-level spatio-temporal features which efficiently capture relevant local dynamics. Features from each window are represented as a Fisher vector, which captures first and second order statistics. Instead of directly classifying each Fisher vector, it is converted into a vector of class probabilities.…
Knowledge-guided Disentanglement with Atomic Actions for Action Recognition
Xidian University（西安电子科技大学）；National University of Defense Technology（国防科技大学）；Human Institute of Advanced Technologyy（人类高级技术研究院）；Shanghai Road Transport Development Center（上海市道路运输发展中心）
Indian Institute of Technology Dharwad（达瓦德印度理工学院）；Indian Institute of Techonology Roorkee（鲁尔基印度理工学院）；UltraInstinct AI（超本能人工智能公司）
We introduce Knowledge Fusion Transformers for video action classification. We present a self-attention based feature enhancer to fuse action knowledge in 3D inception based spatio-temporal context of the video clip intended to be classified. We show, how using only one stream networks and with little or, no pretraining can pave the way for a performance close to the current state-of-the-art. Additionally, we present how different self-attention architectures used at different levels of the network can be blended-in to enhance feature representation. Our architecture is trained and evaluated o…
Few-shot action recognition in videos is challenging for its lack of supervision and difficulty in generalizing to unseen actions. To address this task, we propose a simple yet effective method, called knowledge prompting, which leverages commonsense knowledge of actions from external resources to prompt a powerful pre-trained vision-language model for few-shot classification. We first collect large-scale language descriptions of actions, defined as text proposals, to build an action knowledge base. The collection of text proposals is done by filling in handcraft sentence templates with extern…
Zhejiang University-University of Illinois at Urbana-Champaign Institute, Zhejiang University（浙江大学伊利诺伊大学厄巴纳香槟校区联合学院，浙江大学）
Video-based action recognition is one of the most popular topics in computer vision. With recent advances of selfsupervised video representation learning approaches, action recognition usually follows a two-stage training framework, i.e., self-supervised pre-training on large-scale unlabeled sets and transfer learning on a downstream labeled set. However, catastrophic forgetting of the pre-trained knowledge becomes the main issue in the downstream transfer learning of action recognition, resulting in a sub-optimal solution. In this paper, to alleviate the above issue, we propose a novel transf…
Stanford University（斯坦福大学）；Massachusetts Institute of Technology（麻省理工学院）；Purdue University（普渡大学）
We present a system that demonstrates how the compositional structure of events, in concert with the compositional structure of language, can interplay with the underlying focusing mechanisms in video action recognition, thereby providing a medium, not only for top-down and bottom-up integration, but also for multi-modal integration between vision and language. We show how the roles played by participants (nouns), their characteristics (adjectives), the actions performed (verbs), the manner of such actions (adverbs), and changing spatial relations between participants (prepositions) in the for…
University of California, Berkeley（加州大学伯克利分校）；Amazon Alexa AI（亚马逊Alexa人工智能部门）；Fujitsu Laboratories Ltd.（富士通实验室有限公司）；Pennsylvania State University（宾夕法尼亚州立大学）
Action in video usually involves the interaction of human with objects. Action labels are typically composed of various combinations of verbs and nouns, but we may not have training data for all possible combinations. In this paper, we aim to improve the generalization ability of the compositional action recognition model to novel verbs or novel nouns that are unseen during training time, by leveraging the power of knowledge graphs. Previous work utilizes verb-noun compositional action nodes in the knowledge graph, making it inefficient to scale since the number of compositional action nodes g…
MIFI: MultI-camera Feature Integration for Roust 3D Distracted Driver Activity Recognition
High Magnetic Field Laboratory, HFIPS, Chinese Academy of Sciences（中国科学院合肥物质科学研究院强磁场科学中心）；University of Science and Technology of China（中国科学技术大学）；High Magnetic Field Laboratory of Anhui Province（安徽省强磁场实验室）
In real-world object recognition, there are numerous object classes to be recognized. Conventional image recognition based on supervised learning can only recognize object classes that exist in the training data, and thus has limited applicability in the real world. On the other hand, humans can recognize novel objects by asking questions and acquiring knowledge about them. Inspired by this, we study a framework for acquiring external knowledge through question generation that would help the model instantly recognize novel objects. Our pipeline consists of two components: the Object Classifier…
We investigate different approaches to integrating object recognition and planning in a tabletop manipulation domain with the set of objects used in the 2012 RoboCup@Work competition. Results of our preliminary experiments show that, with some approaches, close integration of perception and planning improves the quality of plans, as well as the computation times of feasible plans.
Beijing University of Technology（北京工业大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
Most existing group activity recognition methods construct spatial-temporal relations merely based on visual representation. Some methods introduce extra knowledge, such as action labels, to build semantic relations and use them to refine the visual presentation. However, the knowledge they explored just stay at the semantic-level, which is insufficient for pursing notable accuracy. In this paper, we propose to exploit knowledge concretization for the group activity recognition, and develop a novel Knowledge Augmented Relation Inference framework that can effectively use the concretized knowle…
Gwangju Institute of Science and Technology (GIST)（光州科学技术院）
Deep learning has achieved outstanding performance for face recognition benchmarks, but performance reduces significantly for low resolution (LR) images. We propose an attention similarity knowledge distillation approach, which transfers attention maps obtained from a high resolution (HR) network as a teacher into an LR network as a student to boost LR recognition performance. Inspired by humans being able to approximate an object's region from an LR image based on prior knowledge obtained from HR images, we designed the knowledge distillation loss using the cosine similarity to make the stude…
YITU Technology（依图科技）；Northeastern University of China（中国东北大学）
Knowledge Distillation (KD) refers to transferring knowledge from a large model to a smaller one, which is widely used to enhance model performance in machine learning. It tries to align embedding spaces generated from the teacher and the student model (i.e. to make images corresponding to the same semantics share the same embedding across different models). In this work, we focus on its application in face recognition. We observe that existing knowledge distillation models optimize the proxy tasks that force the student to mimic the teacher's behavior, instead of directly optimizing the face …
National Center for Mathematics and Interdisciplinary Sciences, Academy of Mathematics and Systems Science, CAS（中国科学院数学与系统科学研究院国家数学与交叉科学中心）；School of Mathematics Sciences, University of Chinese Academy of Sciences（中国科学院大学数学科学学院）
Nonnegative matrix factorization (NMF) is a powerful tool in data exploratory analysis by discovering the hidden features and part-based patterns from high-dimensional data. NMF and its variants have been successfully applied into diverse fields such as pattern recognition, signal processing, data mining, bioinformatics and so on. Recently, NMF has been extended to analyze multiple matrices simultaneously. However, a unified framework is still lacking. In this paper, we introduce a sparse multiple relationship data regularized joint matrix factorization (JMF) framework and two adapted predicti…
National Yang Ming Chiao Tung University（国立阳明交通大学）
Recently, Transformer-based methods have been utilized to improve the performance of human action recognition. However, most of these studies assume that multi-view data is complete, which may not always be the case in real-world scenarios. Therefore, this paper presents a novel Multi-view Knowledge Distillation Transformer (MKDT) framework that consists of a teacher network and a student network. This framework aims to handle incomplete human action problems in real-world applications. Specifically, the multi-view knowledge distillation transformer uses a hierarchical vision transformer with …
Percept, Chat, and then Adapt: Multimodal Knowledge Transfer of Foundation Models for Open-World Video Recognition
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；the School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Shanghai AI Laboratory（上海人工智能实验室）
Real-world scenarios pose several challenges to deep learning based computer vision techniques despite their tremendous success in research. Deeper models provide better performance, but are challenging to deploy and knowledge distillation allows us to train smaller models with minimal loss in performance. The model also has to deal with open set samples from classes outside the ones it was trained on and should be able to identify them as unknown samples while classifying the known ones correctly. Finally, most existing image recognition research focuses only on using two-dimensional snapshot…
Fraunhofer Institute for Integrated Circuits IIS（弗劳恩霍夫集成电路研究所）；University of Bamberg（班贝格大学）
Neural networks are widely adopted, yet the integration of domain knowledge is still underutilized. We propose to integrate domain knowledge about co-occurring facial movements as a constraint in the loss function to enhance the training of neural networks for affect recognition. As the co-ccurrence patterns tend to be similar across datasets, applying our method can lead to a higher generalizability of models and a lower risk of overfitting. We demonstrate this by showing performance increases in cross-dataset testing for various datasets. We also show the applicability of our method for cali…
Many real-world applications of image recognition require multi-label learning, whose goal is to find all labels in an image. Thus, robustness of such systems to adversarial image perturbations is extremely important. However, despite a large body of recent research on adversarial attacks, the scope of the existing works is mainly limited to the multi-class setting, where each image contains a single label. We show that the naive extensions of multi-class attacks to the multi-label setting lead to violating label relationships, modeled by a knowledge graph, and can be detected using a consiste…
This paper demonstrates a novel approach to improve face-recognition pose-invariance using semantic-segmentation features. The proposed Seg-Distilled-ID network jointly learns identification and semantic-segmentation tasks, where the segmentation task is then "distilled" (MobileNet encoder). Performance is benchmarked against three state-of-the-art encoders on a publicly available data-set emphasizing head-pose variations. Experimental evaluations show the Seg-Distilled-ID network shows notable robustness benefits, achieving 99.9% test-accuracy in comparison to 81.6% on ResNet-101, 96.1% on VG…
Beihang University（北京航空航天大学）；SenseTime Group Limited（商汤集团有限公司）
Knowledge distillation is an effective method to improve the performance of a lightweight neural network (i.e., student model) by transferring the knowledge of a well-performed neural network (i.e., teacher model), which has been widely applied in many computer vision tasks, including face recognition. Nevertheless, the current face recognition distillation methods usually utilize the Feature Consistency Distillation (FCD) (e.g., L2 distance) on the learned embeddings extracted by the teacher and student models for each sample, which is not able to fully transfer the knowledge from the teacher…
The University of Sydney（悉尼大学）；Baidu Inc.（百度公司）；Zhejiang University（浙江大学）；University of Chinese Academy of Sciences（中国科学院大学）；Shanghai AI Laboratory（上海人工智能实验室）
Vision-language models (VLMs) pre-trained on large-scale image-text pairs have demonstrated impressive transferability on various visual tasks. Transferring knowledge from such powerful VLMs is a promising direction for building effective video recognition models. However, current exploration in this field is still limited. We believe that the greatest value of pre-trained VLMs lies in building a bridge between visual and textual domains. In this paper, we propose a novel framework called BIKE, which utilizes the cross-modal bridge to explore bidirectional knowledge: i) We introduce the Video …
VicKAM: Visual Conceptual Knowledge Guided Action Map for Weakly Supervised Group Activity Recognition
School of Information Science and Technology, Beijing University of Technology（北京工业大学信息科学与技术学院）；Institute of automation, Chinese Academy of Science（中国科学院自动化研究所）
EPIR: An Efficient Patch Tokenization, Integration and Representation Framework for Micro-expression Recognition
School of Software, Northwestern Polytechnical University（西北工业大学软件学院）；School of Computer Science, Northwestern Polytechnical University（西北工业大学计算机学院）；School of Computer Science and Technology, Xi'an Jiaotong University（西安交通大学计算机科学与技术学院）；School of Science, Edith Cowan University（埃迪斯科文大学理学院）
Nanjing University（南京大学）；SenseTime Research（商汤科技研究院）；Shanghai AI Laboratory（上海人工智能实验室）
Video recognition in an open and dynamic world is quite challenging, as we need to handle different settings such as close-set, long-tail, few-shot and open-set. By leveraging semantic knowledge from noisy text descriptions crawled from the Internet, we focus on the general video recognition (GVR) problem of solving different recognition tasks within a unified framework. The core contribution of this paper is twofold. First, we build a comprehensive video recognition benchmark of Kinetics-GVR, including four sub-task datasets to cover the mentioned settings. To facilitate the research of GVR, …
How Knowledge Distillation Mitigates the Synthetic Gap in Fair Face Recognition
INESC TEC；Faculty of Engineering of the University of Porto（波尔图大学工程学院）；Faculty of Electrical Engineering and Computer Science, University of Maribor（马里博尔大学电气工程与计算机科学学院）
Sun Yat-sen University（中山大学）；SenseTime Research（商汤科技研究院）；Guilin University of Electronic Technology（桂林电子科技大学）
Humans can naturally understand an image in depth with the aid of rich knowledge accumulated from daily lives or professions. For example, to achieve fine-grained image recognition (e.g., categorizing hundreds of subordinate categories of birds) usually requires a comprehensive visual concept organization including category labels and part-level attributes. In this work, we investigate how to unify rich professional knowledge with deep neural network architectures and propose a Knowledge-Embedded Representation Learning (KERL) framework for handling the problem of fine-grained image recognitio…
Visual place recognition (VPR) is usually considered as a specific image retrieval problem. Limited by existing training frameworks, most deep learning-based works cannot extract sufficiently stable global features from RGB images and rely on a time-consuming re-ranking step to exploit spatial structural information for better performance. In this paper, we propose StructVPR, a novel training architecture for VPR, to enhance structural knowledge in RGB global features and thus improve feature stability in a constantly changing environment. Specifically, StructVPR uses segmentation images as a …
Deep convolutional neural networks (DCNNs) have achieved great success in various computer vision and pattern recognition applications, including those for handwritten Chinese character recognition (HCCR). However, most current DCNN-based HCCR approaches treat the handwritten sample simply as an image bitmap, ignoring some vital domain-specific information that may be useful but that cannot be learnt by traditional networks. In this paper, we propose an enhancement of the DCNN approach to online HCCR by incorporating a variety of domain-specific knowledge, including deformation, non-linear nor…
Huazhong University of Science and Technology（华中科技大学）；Tencent YouTu Lab（腾讯优图实验室）
Recently, the semantics of scene text has been proven to be essential in fine-grained image classification. However, the existing methods mainly exploit the literal meaning of scene text for fine-grained recognition, which might be irrelevant when it is not significantly related to objects/scenes. We propose an end-to-end trainable network that mines implicit contextual knowledge behind scene text image and enhance the semantics and correlation to fine-tune the image representation. Unlike the existing methods, our model integrates three modalities: visual feature extraction, text semantics ex…
Knowledge distillation (KD) is a widely-used technique that utilizes large networks to improve the performance of compact models. Previous KD approaches usually aim to guide the student to mimic the teacher's behavior completely in the representation space. However, such one-to-one corresponding constraints may lead to inflexible knowledge transfer from the teacher to the student, especially those with low model capacities. Inspired by the ultimate goal of KD methods, we propose a novel Evaluation oriented KD method (EKD) for deep face recognition to directly reduce the performance gap between…
Hanoi University of Science and Technology（河内科技大学）；VinUniversity（Vin大学）
Identifying pills given their captured images under various conditions and backgrounds has been becoming more and more essential. Several efforts have been devoted to utilizing the deep learning-based approach to tackle the pill recognition problem in the literature. However, due to the high similarity between pills' appearance, misrecognition often occurs, leaving pill recognition a challenge. To this end, in this paper, we introduce a novel approach named PIKA that leverages external knowledge to enhance pill recognition accuracy. Specifically, we address a practical scenario (which we call …
Linear building pattern recognition via spatial knowledge graph
Institute of Electronic, Chinese Academy of Sciences（中国科学院电子学研究所）；School of Resources and Environment Science, Wuhan University（武汉大学资源与环境科学学院）；School of Software Engineering, Shenzhen Institute of Information Technology（深圳信息职业技术学院软件学院）；School of Information and Communication Engineering, Beijing University of Posts and Telecommunications（北京邮电大学信息与通信工程学院）
Nanyang Technological University（南洋理工大学）；Central South University（中南大学）；Singapore University of Technology and Design（新加坡科技设计大学）
Deep learning techniques have shown their superior performance in dermatologist clinical inspection. Nevertheless, melanoma diagnosis is still a challenging task due to the difficulty of incorporating the useful dermatologist clinical knowledge into the learning process. In this paper, we propose a novel knowledge-aware deep framework that incorporates some clinical knowledge into collaborative learning of two important melanoma diagnosis tasks, i.e., skin lesion segmentation and melanoma recognition. Specifically, to exploit the knowledge of morphological expressions of the lesion region and …
Inferring High-level Geographical Concepts via Knowledge Graph and Multi-scale Data Integration: A Case Study of C-shaped Building Pattern Recognition
Aerospace Information Research Institute, Chinese Academy of Sciences（中国科学院空天信息创新研究院）；School of Resource and Environment Science, Wuhan University（武汉大学资源与环境科学学院）；School of Information and Communication Engineering, Beijing University of Posts and Telecommunications（北京邮电大学信息与通信工程学院）；Institute of Remote Sensing and GIS, Peking University（北京大学遥感与地理信息系统研究所）
Dalian University of Technology（大连理工大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen)（香港中文大学（深圳））
In this work, we introduce a novel strategy for long-tail recognition that addresses the tail classes' few-shot problem via training-free knowledge transfer. Our objective is to transfer knowledge acquired from information-rich common classes to semantically similar, and yet data-hungry, rare classes in order to obtain stronger tail class representations. We leverage the fact that class prototypes and learned cosine classifiers provide two different, complementary representations of class cluster centres in feature space, and use an attention mechanism to select and recompose learned classifie…
Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS（中国科学院计算技术研究所中国科学院智能信息处理重点实验室）
The central role of food in our individual and social life, combined with recent technological advances, has motivated a growing interest in applications that help to better monitor dietary habits as well as the exploration and retrieval of food-related information. We review how visual content, context and external knowledge can be integrated effectively into food-oriented applications, with special focus on recipe analysis and retrieval, food recommendation, and the restaurant context as emerging directions.
Human Activity Recognition is a field of research where input data can take many forms. Each of the possible input modalities describes human behaviour in a different way, and each has its own strengths and weaknesses. We explore the hypothesis that leveraging multiple modalities can lead to better recognition. Since manual annotation of input data is expensive and time-consuming, the emphasis is made on self-supervised methods which can learn useful feature representations without any ground truth labels. We extend a number of recent contrastive self-supervised approaches for the task of Huma…
Many machine learning algorithms have been developed in recent years to enhance the performance of a model in different aspects of artificial intelligence. But the problem persists due to inadequate data and resources. Integrating knowledge in a machine learning model can help to overcome these obstacles up to a certain degree. Incorporating knowledge is a complex task though because of various forms of knowledge representation. In this paper, we will give a brief overview of these different forms of knowledge integration and their performance in certain machine learning tasks.
National Central University（国立中央大学）；Thai Nguyen University（太原大学）
Knowledge distillation is an effective transfer of knowledge from a heavy network (teacher) to a small network (student) to boost students' performance. Self-knowledge distillation, the special case of knowledge distillation, has been proposed to remove the large teacher network training process while preserving the student's performance. This paper introduces a novel Self-knowledge distillation approach via Siamese representation learning, which minimizes the difference between two representation vectors of the two different views from a given sample. Our proposed method, SKD-SRL, utilizes bo…
Due to the collection of big data and the development of deep learning, research to predict human emotions in the wild is being actively conducted. We designed a multi-task model using ABAW dataset to predict valence-arousal, expression, and action unit through audio data and face images at in real world. We trained model from the incomplete label by applying the knowledge distillation technique. The teacher model was trained as a supervised learning method, and the student model was trained by using the output of the teacher model as a soft label. As a result we achieved 2.40 in Multi Task Le…
