In the world of action recognition research, one primary focus has been on how to construct and train networks to model the spatial-temporal volume of an input video. These methods typically uniformly sample a segment of an input clip (along the temporal dimension). However, not all parts of a video are equally important to determine the action in the clip. In this work, we focus instead on learning where to extract features, so as to focus on the most informative parts of the video. We propose a method called the non-uniform temporal aggregation (NUTA), which aggregates features only from informative temporal segments. We also introduce a synchronization method that allows our NUTA features to be temporally aligned with traditional uniformly sampled video features, so that both local and clip-level features can be combined. Our model has achieved state-of-the-art performance on four widely used large-scale action-recognition datasets (Kinetics400, Kinetics700, Something-something V2 and Charades). In addition, we have created a visualization to illustrate how the proposed NUTA method selects only the most relevant parts of a video clip.
Institution for Advanced Computer Studies（高级计算机研究所）；University of Maryland, College Park（马里兰大学帕克分校）
We present Temporal Aggregation Network (TAN) which decomposes 3D convolutions into spatial and temporal aggregation blocks. By stacking spatial and temporal convolutions repeatedly, TAN forms a deep hierarchical representation for capturing spatio-temporal information in videos. Since we do not apply 3D convolutions in each layer but only apply temporal aggregation blocks once after each spatial downsampling layer in the network, we significantly reduce the model complexity. The use of dilated convolutions at different resolutions of the network helps in aggregating multi-scale spatio-tempora…
Skeleton-based action recognition methods are limited by the semantic extraction of spatio-temporal skeletal maps. However, current methods have difficulty in effectively combining features from both temporal and spatial graph dimensions and tend to be thick on one side and thin on the other. In this paper, we propose a Temporal-Channel Aggregation Graph Convolutional Networks (TCA-GCN) to learn spatial and temporal topologies dynamically and efficiently aggregate topological features in different temporal and channel dimensions for skeleton-based action recognition. We use the Temporal Aggreg…
Temporal reasoning is an important aspect of video analysis. 3D CNN shows good performance by exploring spatial-temporal features jointly in an unconstrained way, but it also increases the computational cost a lot. Previous works try to reduce the complexity by decoupling the spatial and temporal filters. In this paper, we propose a novel decomposition method that decomposes the feature channels into spatial and temporal groups in parallel. This decomposition can make two groups focus on static and dynamic cues separately. We call this grouped spatial-temporal aggregation (GST). This decomposi…
Skeleton-based human action recognition has recently drawn increasing attentions with the availability of large-scale skeleton datasets. The most crucial factors for this task lie in two aspects: the intra-frame representation for joint co-occurrences and the inter-frame representation for skeletons' temporal evolutions. In this paper we propose an end-to-end convolutional co-occurrence feature learning framework. The co-occurrence features are learned with a hierarchical methodology, in which different levels of contextual information are aggregated gradually. Firstly point-level information …
Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会）；University of Trento（特伦托大学）；Computer Vision Center（计算机视觉中心）；University of Barcelona（巴塞罗那大学）
Most action recognition methods base on a) a late aggregation of frame level CNN features using average pooling, max pooling, or RNN, among others, or b) spatio-temporal aggregation via 3D convolutions. The first assume independence among frame features up to a certain level of abstraction and then perform higher-level aggregation, while the second extracts spatio-temporal features from grouped frames as early fusion. In this paper we explore the space in between these two, by letting adjacent feature branches interact as they develop into the higher level representation. The interaction happe…
Tencent（腾讯）；Nanjing University（南京大学）；Southern University of Science and Technology（南方科技大学）
Temporal modeling is key for action recognition in videos. It normally considers both short-range motions and long-range aggregations. In this paper, we propose a Temporal Excitation and Aggregation (TEA) block, including a motion excitation (ME) module and a multiple temporal aggregation (MTA) module, specifically designed to capture both short- and long-range temporal evolution. In particular, for short-range motion modeling, the ME module calculates the feature-level temporal differences from spatiotemporal features. It then utilizes the differences to excite the motion-sensitive channels o…
Modelling various spatio-temporal dependencies is the key to recognising human actions in skeleton sequences. Most existing methods excessively relied on the design of traversal rules or graph topologies to draw the dependencies of the dynamic joints, which is inadequate to reflect the relationships of the distant yet important joints. Furthermore, due to the locally adopted operations, the important long-range temporal information is therefore not well explored in existing works. To address this issue, in this work we propose LSTA-Net: a novel Long short-term Spatio-Temporal Aggregation Netwo…
University of Wollongong（卧龙岗大学）；Motovis Inc（魔视智能科技有限公司）；Chinese Academy of Sciences（中国科学院）；National University of Defense Technology（国防科技大学）
A novel deep neural network training paradigm that exploits the conjoint information in multiple heterogeneous sources is proposed. Specifically, in a RGB-D based action recognition task, it cooperatively trains a single convolutional neural network (named c-ConvNet) on both RGB visual features and depth features, and deeply aggregates the two kinds of features for action recognition. Differently from the conventional ConvNet that learns the deep separable features for homogeneous modality-based classification with only one softmax loss function, the c-ConvNet enhances the discriminative power…
Most of the current action recognition algorithms are based on deep networks which stack multiple convolutional, pooling and fully connected layers. While convolutional and fully connected operations have been widely studied in the literature, the design of pooling operations that handle action recognition, with different sources of temporal granularity in action categories, has comparatively received less attention, and existing solutions rely mainly on max or averaging operations. The latter are clearly powerless to fully exhibit the actual temporal granularity of action categories and there…
Trunk-branch Contrastive Network with Multi-view Deformable Aggregation for Multi-view Action Recognition
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；University of Chinese Academy of Sciences（中国科学院大学）；School of Mechanical Engineering and Automation, Harbin Institute of Technology at Shenzhen（哈尔滨工业大学（深圳）机械工程与自动化学院）
Hong Kong University of Science and Technology（香港科技大学）；Kauishou（快手）
Despite excellent progress has been made, the performance on action recognition still heavily relies on specific datasets, which are difficult to extend new action classes due to labor-intensive labeling. Moreover, the high diversity in Spatio-temporal appearance requires robust and representative action feature aggregation and attention. To address the above issues, we focus on atomic actions and propose a novel model for semi-supervised few-shot atomic action recognition. Our model features unsupervised and contrastive video embedding, loose action alignment, multi-head feature comparison, a…
Efficient long-short temporal modeling is key for enhancing the performance of action recognition task. In this paper, we propose a new two-stream action recognition network, termed as MENet, consisting of a Motion Enhancement (ME) module and a Video-level Aggregation (VLA) module to achieve long-short temporal modeling. Specifically, motion representations have been proved effective in capturing short-term and high-frequency action. However, current motion representations are calculated from adjacent frames, which may have poor interpretation and bring useless information (noisy or blank). Th…
MIT-IBM Waston AI Lab（MIT-IBM沃森人工智能实验室）；IBM T.J. Waston Research Center（IBM托马斯·J·沃森研究中心）
Current state-of-the-art models for video action recognition are mostly based on expensive 3D ConvNets. This results in a need for large GPU clusters to train and evaluate such architectures. To address this problem, we present a lightweight and memory-friendly architecture for action recognition that performs on par with or better than current architectures by using only a fraction of resources. The proposed architecture is based on a combination of a deep subnet operating on low-resolution frames with a compact subnet operating on high-resolution frames, allowing for high efficiency and accu…
Inria（法国国家信息与自动化研究所）；Université Côte d’Azur（蔚蓝海岸大学）；Toyota Motor Europe（丰田汽车欧洲公司）
Taking advantage of human pose data for understanding human activities has attracted much attention these days. However, state-of-the-art pose estimators struggle in obtaining high-quality 2D or 3D pose data due to occlusion, truncation and low-resolution in real-world un-annotated videos. Hence, in this work, we propose 1) a Selective Spatio-Temporal Aggregation mechanism, named SST-A, that refines and smooths the keypoint locations extracted by multiple expert pose estimators, 2) an effective weakly-supervised self-training framework which leverages the aggregated poses as pseudo ground-trut…
The University of Sydney（悉尼大学）；SenseTime Computer Vision Research Group（商汤科技计算机视觉研究组）；University of Chinese Academy of Sciences（中国科学院大学）；CASIA（中国科学院自动化研究所）
Spatial-temporal graphs have been widely used by skeleton-based action recognition algorithms to model human action dynamics. To capture robust movement patterns from these graphs, long-range and multi-scale context aggregation and spatial-temporal dependency modeling are critical aspects of a powerful feature extractor. However, existing methods have limitations in achieving (1) unbiased long-range joint relationship modeling under multi-scale operators and (2) unobstructed cross-spacetime information flow for capturing complex spatial-temporal dependencies. In this work, we present (1) a sim…
This work targets human action recognition in video. While recent methods typically represent actions by statistics of local video features, here we argue for the importance of a representation derived from human pose. To this end we propose a new Pose-based Convolutional Neural Network descriptor (P-CNN) for action recognition. The descriptor aggregates motion and appearance information along tracks of human body parts. We investigate different schemes of temporal aggregation and experiment with P-CNN features obtained both for automatically estimated and manually annotated human poses. We ev…
Fondazione Bruno Kessler - FBK（布鲁诺·凯斯勒基金会（FBK））；Computer Vision Center（计算机视觉中心）；Universitat de Barcelona（巴塞罗那大学）
In this report we describe the technical details of our submission to the EPIC-Kitchens Action Recognition 2020 Challenge. To participate in the challenge we deployed spatio-temporal feature extraction and aggregation models we have developed recently: Gate-Shift Module (GSM) [1] and EgoACO, an extension of Long Short-Term Attention (LSTA) [2]. We design an ensemble of GSM and EgoACO model families with different backbones and pre-training to generate the prediction scores. Our submission, visible on the public leaderboard with team name FBK-HUPBA, achieved a top-1 action recognition accuracy …
In this paper we present an event aggregation strategy to convert the output of an event camera into frames processable by traditional Computer Vision algorithms. The proposed method first generates sequences of intermediate binary representations, which are then losslessly transformed into a compact format by simply applying a binary-to-decimal conversion. This strategy allows us to encode temporal information directly into pixel values, which are then interpreted by deep learning models. We apply our strategy, called Temporal Binary Representation, to the task of Gesture Recognition, obtaini…
In this paper, we introduce a novel hierarchical aggregation design that captures different levels of temporal granularity in action recognition. Our design principle is coarse-to-fine and achieved using a tree-structured network; as we traverse this network top-down, pooling operations are getting less invariant but timely more resolute and well localized. Learning the combination of operations in this network -- which best fits a given ground-truth -- is obtained by solving a constrained minimization problem whose solution corresponds to the distribution of weights that capture the contribut…
Samsung AI Center Cambridge UK（三星剑桥人工智能中心（英国））；Fondazione Bruno Kessler - FBK Trento Italy（布鲁诺·凯斯勒基金会（FBK）特伦托（意大利））；Computer Vision Center Barcelona Spain（巴塞罗那计算机视觉中心（西班牙））；Universitat de Barcelona Barcelona Spain（巴塞罗那大学（西班牙））
This report presents the technical details of our submission to the EPIC-Kitchens-100 Action Recognition Challenge 2021. To participate in the challenge we deployed spatio-temporal feature extraction and aggregation models we have developed recently: GSF and XViT. GSF is an efficient spatio-temporal feature extracting module that can be plugged into 2D CNNs for video action recognition. XViT is a convolution free video feature extractor based on transformer architecture. We design an ensemble of GSF and XViT model families with different backbones and pretraining to generate the prediction sco…
This paper addresses the task of unsupervised learning of representations for action recognition in videos. Previous works proposed to utilize future prediction, or other domain-specific objectives to train a network, but achieved only limited success. In contrast, in the relevant field of image representation learning, simpler, discrimination-based methods have recently bridged the gap to fully-supervised performance. We first propose to adapt two top performing objectives in this class - instance recognition and local aggregation, to the video domain. In particular, the latter approach itera…
University of Bristol（布里斯托大学）；University of Oxford（牛津大学）
We focus on multi-modal fusion for egocentric action recognition, and propose a novel architecture for multi-modal temporal-binding, i.e. the combination of modalities within a range of temporal offsets. We train the architecture with three modalities -- RGB, Flow and Audio -- and combine them with mid-level fusion alongside sparse temporal sampling of fused representations. In contrast with previous works, modalities are fused before temporal aggregation, with shared modality and fusion weights over time. Our proposed architecture is trained end-to-end, outperforming individual modalities as …
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…
Recurrent networks have been successful in analyzing temporal data and have been widely used for video analysis. However, for video face recognition, where the base CNNs trained on large-scale data already provide discriminative features, using Long Short-Term Memory (LSTM), a popular recurrent network, for feature learning could lead to overfitting and degrade the performance instead. We propose a Recurrent Embedding Aggregation Network (REAN) for set to set face recognition. Compared with LSTM, REAN is robust against overfitting because it only learns how to aggregate the pre-trained embeddi…
In this paper, we propose a novel method, aggregation cross-entropy (ACE), for sequence recognition from a brand new perspective. The ACE loss function exhibits competitive performance to CTC and the attention mechanism, with much quicker implementation (as it involves only four fundamental formulas), faster inference\back-propagation (approximately O(1) in parallel), less storage requirement (no parameter and negligible runtime memory), and convenient employment (by replacing CTC with ACE). Furthermore, the proposed ACE loss function exhibits two noteworthy properties: (1) it can be directly …
We propose a new approach to video face recognition. Our component-wise feature aggregation network (C-FAN) accepts a set of face images of a subject as an input, and outputs a single feature vector as the face representation of the set for the recognition task. The whole network is trained in two steps: (i) train a base CNN for still image face recognition; (ii) add an aggregation module to the base network to learn the quality value for each feature component, which adaptively aggregates deep feature vectors into a single vector to represent the face in a video. C-FAN automatically learns to…
Video-FocalNets: Spatio-Temporal Focal Modulation for Video Action Recognition
Mohamed bin Zayed University of AI（穆罕默德·本·扎耶德人工智能大学）；Australian National University（澳大利亚国立大学）；University of Central Florida（中佛罗里达大学）；Linköping University（林雪平大学）
Modern neural networks are powerful predictive models. However, when it comes to recognizing that they may be wrong about their predictions, they perform poorly. For example, for one of the most common activation functions, the ReLU and its variants, even a well-calibrated model can produce incorrect but high confidence predictions. In the related task of action recognition, most current classification methods are based on clip-level classifiers that densely sample a given video for non-overlapping, same-sized clips and aggregate the results using an aggregation function - typically averaging …
Shenzhen University（深圳大学）；Johns Hopkins University（约翰斯·霍普金斯大学）；Australian National University（澳大利亚国立大学）
Visual place recognition is challenging in the urban environment and is usually viewed as a large scale image retrieval task. The intrinsic challenges in place recognition exist that the confusing objects such as cars and trees frequently occur in the complex urban scene, and buildings with repetitive structures may cause over-counting and the burstiness problem degrading the image representations. To address these problems, we present an Attention-based Pyramid Aggregation Network (APANet), which is trained in an end-to-end manner for place recognition. One main component of APANet, the spati…
National University of Kyiv-Mohyla Academy（基辅莫希拉国立大学）；Proxet（Proxet公司）；Institute of Software Systems of NAS of Ukraine（乌克兰国家科学院软件系统研究所）；GIPHY（GIPHY公司）；National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute”（乌克兰国立技术大学“ Igor Sikorsky基辅理工学院”）
Models based on self-attention mechanisms have been successful in analyzing temporal data and have been widely used in the natural language domain. We propose a new model architecture for video face representation and recognition based on a self-attention mechanism. Our approach could be used for video with single and multiple identities. To the best of our knowledge, no one has explored the aggregation approaches that consider the video with multiple identities. The proposed approach utilizes existing models to get the face representation for each video frame, e.g., ArcFace and MobileFaceNet,…
TraRA: Trajectory-level Recognition Aggregation for Video Text Spotting in Urban Surveillance
RIKEN（日本理化学研究所）；Hanoi University of Science and Technology（河内科学技术大学）；Nagoya University（名古屋大学）；Lawrence Technological University（劳伦斯技术大学）；Ritsumeikan University（立命馆大学）
Capturing the dependencies between joints is critical in skeleton-based action recognition task. Transformer shows great potential to model the correlation of important joints. However, the existing Transformer-based methods cannot capture the correlation of different joints between frames, which the correlation is very useful since different body parts (such as the arms and legs in "long jump") between adjacent frames move together. Focus on this problem, A novel spatio-temporal tuples Transformer (STTFormer) method is proposed. The skeleton sequence is divided into several parts, and several…
Beijing Jiaotong University（北京交通大学）；University of Technology Sydney（悉尼科技大学）
Gait recognition is one of the most important biometric technologies and has been applied in many fields. Recent gait recognition frameworks represent each gait frame by descriptors extracted from either global appearances or local regions of humans. However, the representations based on global information often neglect the details of the gait frame, while local region based descriptors cannot capture the relations among neighboring regions, thus reducing their discriminativeness. In this paper, we propose a novel feature extraction and fusion framework to achieve discriminative feature repres…
National University of Singapore（新加坡国立大学）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；ByteDance（字节跳动）
Existing long-tailed recognition methods, aiming to train class-balanced models from long-tailed data, generally assume the models would be evaluated on the uniform test class distribution. However, practical test class distributions often violate this assumption (e.g., being either long-tailed or even inversely long-tailed), which may lead existing methods to fail in real applications. In this paper, we study a more practical yet challenging task, called test-agnostic long-tailed recognition, where the training class distribution is long-tailed while the test class distribution is agnostic an…
North China University of Science and Technology（华北理工大学）
The nanoparticle size and distribution information in the SEM images of silicon crystals are generally counted by manual methods. The realization of automatic machine recognition is significant in materials science. This paper proposed a superposition partitioning image recognition method to realize automatic recognition and information statistics of silicon crystal nanoparticle SEM images. Especially for the complex and highly aggregated characteristics of silicon crystal particle size, an accurate recognition step and contour statistics method based on morphological processing are given. Thi…
Microsoft Research（微软研究院）；The Australian National University（澳大利亚国立大学）；Beijing Institute of Technology（北京理工大学）
This paper presents a Neural Aggregation Network (NAN) for video face recognition. The network takes a face video or face image set of a person with a variable number of face images as its input, and produces a compact, fixed-dimension feature representation for recognition. The whole network is composed of two modules. The feature embedding module is a deep Convolutional Neural Network (CNN) which maps each face image to a feature vector. The aggregation module consists of two attention blocks which adaptively aggregate the feature vectors to form a single feature inside the convex hull spann…
Beijing University of Posts and Telecommucations（北京邮电大学）
Video-based person recognition is challenging due to persons being blocked and blurred, and the variation of shooting angle. Previous research always focused on person recognition on still images, ignoring similarity and continuity between video frames. To tackle the challenges above, we propose a novel Frame Aggregation and Multi-Modal Fusion (FAMF) framework for video-based person recognition, which aggregates face features and incorporates them with multi-modal information to identify persons in videos. For frame aggregation, we propose a novel trainable layer based on NetVLAD (named Attent…
SuperPlace: The Renaissance of Classical Feature Aggregation for Visual Place Recognition in the Era of Foundation Models
Southern University of Science and Technology（南方科技大学）；Peng Cheng Laboratory（鹏城实验室）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Cambridge University（剑桥大学）
Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University（西安交通大学人工智能与机器人研究所）
Visual place recognition is a challenging task for applications such as autonomous driving navigation and mobile robot localization. Distracting elements presenting in complex scenes often lead to deviations in the perception of visual place. To address this problem, it is crucial to integrate information from only task-relevant regions into image representations. In this paper, we introduce a novel holistic place recognition model, TransVPR, based on vision Transformers. It benefits from the desirable property of the self-attention operation in Transformers which can naturally aggregate task-…
This paper aims to learn a compact representation of a video for video face recognition task. We make the following contributions: first, we propose a meta attention-based aggregation scheme which adaptively and fine-grained weighs the feature along each feature dimension among all frames to form a compact and discriminative representation. It makes the best to exploit the valuable or discriminative part of each frame to promote the performance of face recognition, without discarding or despising low quality frames as usual methods do. Second, we build a feature aggregation network comprised o…
Event retrieval and recognition in a large corpus of videos necessitates a holistic fixed-size visual representation at the video clip level that is comprehensive, compact, and yet discriminative. It shall comprehensively aggregate information across relevant video frames, while suppress redundant information, leading to a compact representation that can effectively differentiate among different visual events. In search for such a representation, we propose to build a spatially consistent counting grid model to aggregate together deep features extracted from different video frames. The spatial…
The Chinese University of Hong Kong（香港中文大学）；T Stone Robotics Institute, CUHK（香港中文大学T石机器人研究所）
Real-time surgical phase recognition is a fundamental task in modern operating rooms. Previous works tackle this task relying on architectures arranged in spatio-temporal order, however, the supportive benefits of intermediate spatial features are not considered. In this paper, we introduce, for the first time in surgical workflow analysis, Transformer to reconsider the ignored complementary effects of spatial and temporal features for accurate surgical phase recognition. Our hybrid embedding aggregation Transformer fuses cleverly designed spatial and temporal embeddings by allowing for active…
School of Computer Science and Communication Engineering, Jiangsu University（江苏大学计算机科学与通信工程学院）；Department of Computer Science, Wayne State University（韦恩州立大学计算机科学系）
Micro-Expression Recognition (MER) is a challenging task as the subtle changes occur over different action regions of a face. Changes in facial action regions are formed as Action Units (AUs), and AUs in micro-expressions can be seen as the actors in cooperative group activities. In this paper, we propose a novel deep neural network model for objective class-based MER, which simultaneously detects AUs and aggregates AU-level features into micro-expression-level representation through Graph Convolutional Networks (GCN). Specifically, we propose two new strategies in our AU detection module for …
