Spatial convolutions are widely used in numerous deep video models. It fundamentally assumes spatio-temporal invariance, i.e., using shared weights for every location in different frames. This work presents Temporally-Adaptive Convolutions (TAdaConv) for video understanding, which shows that adaptive weight calibration along the temporal dimension is an efficient way to facilitate modelling complex temporal dynamics in videos. Specifically, TAdaConv empowers the spatial convolutions with temporal modelling abilities by calibrating the convolution weights for each frame according to its local and global temporal context. Compared to previous temporal modelling operations, TAdaConv is more efficient as it operates over the convolution kernels instead of the features, whose dimension is an order of magnitude smaller than the spatial resolutions. Further, the kernel calibration brings an increased model capacity. We construct TAda2D and TAdaConvNeXt networks by replacing the 2D convolutions in ResNet and ConvNeXt with TAdaConv, which leads to at least on par or better performance compared to state-of-the-art approaches on multiple video action recognition and localization benchmarks. We also demonstrate that as a readily plug-in operation with negligible computation overhead, TAdaConv can effectively improve many existing video models with a convincing margin.
In the field of action recognition, video clips are always treated as ordered frames for subsequent processing. To achieve spatio-temporal perception, existing approaches propose to embed adjacent temporal interaction in the convolutional layer. The global semantic information can therefore be obtained by stacking multiple local layers hierarchically. However, such global temporal accumulation can only reflect the high-level semantics in deep layers, neglecting the potential low-level holistic clues in shallow layers. In this paper, we first propose to transform a video sequence into a graph to obtain direct long-term dependencies among temporal frames. To preserve sequential information during transformation, we devise a structured graph module (SGM), achieving fine-grained temporal interactions throughout the entire network. In particular, SGM divides the neighbors of each node into several temporal regions so as to extract global structural information with diverse sequential flows. Extensive experiments are performed on standard benchmark datasets, i.e., Something-Something V1 & V2, Diving48, Kinetics-400, UCF101, and HMDB51. The reported performance and analysis demonstrate that SGM can achieve outstanding precision with less computational complexity.
Fine-grained human action recognition is a core research topic in computer vision. Inspired by the recently proposed hierarchy representation of fine-grained actions in FineGym and SlowFast network for action recognition, we propose a novel multi-task network which exploits the FineGym hierarchy representation to achieve effective joint learning and prediction for fine-grained human action recognition. The multi-task network consists of three pathways of SlowOnly networks with gradually increased frame rates for events, sets and elements of fine-grained actions, followed by our proposed integration layers for joint learning and prediction. It is a two-stage approach, where it first learns deep feature representation at each hierarchical level, and is followed by feature encoding and fusion for multi-task learning. Our empirical results on the FineGym dataset achieve a new state-of-the-art performance, with 91.80% Top-1 accuracy and 88.46% mean accuracy for element actions, which are 3.40% and 7.26% higher than the previous best results.
Advancements in deep neural networks have contributed to near perfect results for many computer vision problems such as object recognition, face recognition and pose estimation. However, human action recognition is still far from human-level performance. Owing to the articulated nature of the human body, it is challenging to detect an action from multiple viewpoints, particularly from an aerial viewpoint. This is further compounded by a scarcity of datasets that cover multiple viewpoints of actions. To fill this gap and enable research in wider application areas, we present a multi-viewpoint outdoor action recognition dataset collected from YouTube and our own drone. The dataset consists of 20 dynamic human action classes, 2324 video clips and 503086 frames. All videos are cropped and resized to 720x720 without distorting the original aspect ratio of the human subjects in videos. This dataset should be useful to many research areas including action recognition, surveillance and situational awareness. We evaluated the dataset with a two-stream CNN architecture coupled with a recently proposed temporal pooling scheme called kernelized rank pooling that produces nonlinear feature subspace representations. The overall baseline action recognition accuracy is 74.0%.
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 scores. Our submission, visible on the public leaderboard, achieved a top-1 action recognition accuracy of 44.82%, using only RGB.
We present VideoCLIP, a contrastive approach to pre-train a unified model for zero-shot video and text understanding, without using any labels on downstream tasks. VideoCLIP trains a transformer for video and text by contrasting temporally overlapping positive video-text pairs with hard negatives from nearest neighbor retrieval. Our experiments on a diverse series of downstream tasks, including sequence-level text-video retrieval, VideoQA, token-level action localization, and action segmentation reveal state-of-the-art performance, surpassing prior work, and in some cases even outperforming supervised approaches. Code is made available at https://github.com/pytorch/fairseq/tree/main/examples/MMPT.
The canonical approach to video action recognition dictates a neural model to do a classic and standard 1-of-N majority vote task. They are trained to predict a fixed set of predefined categories, limiting their transferable ability on new datasets with unseen concepts. In this paper, we provide a new perspective on action recognition by attaching importance to the semantic information of label texts rather than simply mapping them into numbers. Specifically, we model this task as a video-text matching problem within a multimodal learning framework, which strengthens the video representation with more semantic language supervision and enables our model to do zero-shot action recognition without any further labeled data or parameters requirements. Moreover, to handle the deficiency of label texts and make use of tremendous web data, we propose a new paradigm based on this multimodal learning framework for action recognition, which we dub "pre-train, prompt and fine-tune". This paradigm first learns powerful representations from pre-training on a large amount of web image-text or video-text data. Then it makes the action recognition task to act more like pre-training problems via prompt engineering. Finally, it end-to-end fine-tunes on target datasets to obtain strong performance. We give an instantiation of the new paradigm, ActionCLIP, which not only has superior and flexible zero-shot/few-shot transfer ability but also reaches a top performance on general action recognition task, achieving 83.8% top-1 accuracy on Kinetics-400 with a ViT-B/16 as the backbone. Code is available at https://github.com/sallymmx/ActionCLIP.git
Temporal sentence grounding in videos(TSGV), which aims to localize one target segment from an untrimmed video with respect to a given sentence query, has drawn increasing attentions in the research community over the past few years. Different from the task of temporal action localization, TSGV is more flexible since it can locate complicated activities via natural languages, without restrictions from predefined action categories. Meanwhile, TSGV is more challenging since it requires both textual and visual understanding for semantic alignment between two modalities(i.e., text and video). In this survey, we give a comprehensive overview for TSGV, which i) summarizes the taxonomy of existing methods, ii) provides a detailed description of the evaluation protocols(i.e., datasets and metrics) to be used in TSGV, and iii) in-depth discusses potential problems of current benchmarking designs and research directions for further investigations. To the best of our knowledge, this is the first systematic survey on temporal sentence grounding. More specifically, we first discuss existing TSGV approaches by grouping them into four categories, i.e., two-stage methods, end-to-end methods, reinforcement learning-based methods, and weakly supervised methods. Then we present the benchmark datasets and evaluation metrics to assess current research progress. Finally, we discuss some limitations in TSGV through pointing out potential problems improperly resolved in the current evaluation protocols, which may push forwards more cutting edge research in TSGV. Besides, we also share our insights on several promising directions, including three typical tasks with new and practical settings based on TSGV.
With the advent of media streaming, video action recognition has become progressively important for various applications, yet at the high expense of requiring large-scale data labelling. To overcome the problem of expensive data labelling, domain adaptation techniques have been proposed that transfers knowledge from fully labelled data (i.e., source domain) to unlabelled data (i.e., target domain). The majority of video domain adaptation algorithms are proposed for closed-set scenarios in which all the classes are shared among the domains. In this work, we propose an open-set video domain adaptation approach to mitigate the domain discrepancy between the source and target data, allowing the target data to contain additional classes that do not belong to the source domain. Different from previous works, which only focus on improving accuracy for shared classes, we aim to jointly enhance the alignment of shared classes and recognition of unknown samples. Towards this goal, class-conditional extreme value theory is applied to enhance the unknown recognition. Specifically, the entropy values of target samples are modelled as generalised extreme value distributions, which allows separating unknown samples lying in the tail of the distribution. To alleviate the negative transfer issue, weights computed by the distance from the sample entropy to the threshold are leveraged in adversarial learning in the sense that confident source and target samples are aligned, and unconfident samples are pushed away. The proposed method has been thoroughly evaluated on both small-scale and large-scale cross-domain video datasets and achieved the state-of-the-art performance.
This paper presents a pure transformer-based approach, dubbed the Multi-Modal Video Transformer (MM-ViT), for video action recognition. Different from other schemes which solely utilize the decoded RGB frames, MM-ViT operates exclusively in the compressed video domain and exploits all readily available modalities, i.e., I-frames, motion vectors, residuals and audio waveform. In order to handle the large number of spatiotemporal tokens extracted from multiple modalities, we develop several scalable model variants which factorize self-attention across the space, time and modality dimensions. In addition, to further explore the rich inter-modal interactions and their effects, we develop and compare three distinct cross-modal attention mechanisms that can be seamlessly integrated into the transformer building block. Extensive experiments on three public action recognition benchmarks (UCF-101, Something-Something-v2, Kinetics-600) demonstrate that MM-ViT outperforms the state-of-the-art video transformers in both efficiency and accuracy, and performs better or equally well to the state-of-the-art CNN counterparts with computationally-heavy optical flow.
Contrastive learning has been widely used to train transformer-based vision-language models for video-text alignment and multi-modal representation learning. This paper presents a new algorithm called Token-Aware Cascade contrastive learning (TACo) that improves contrastive learning using two novel techniques. The first is the token-aware contrastive loss which is computed by taking into account the syntactic classes of words. This is motivated by the observation that for a video-text pair, the content words in the text, such as nouns and verbs, are more likely to be aligned with the visual contents in the video than the function words. Second, a cascade sampling method is applied to generate a small set of hard negative examples for efficient loss estimation for multi-modal fusion layers. To validate the effectiveness of TACo, in our experiments we finetune pretrained models for a set of downstream tasks including text-video retrieval (YouCook2, MSR-VTT and ActivityNet), video action step localization (CrossTask), video action segmentation (COIN). The results show that our models attain consistent improvements across different experimental settings over previous methods, setting new state-of-the-art on three public text-video retrieval benchmarks of YouCook2, MSR-VTT and ActivityNet.
Self-supervised learning has been successfully applied to pre-train video representations, which aims at efficient adaptation from pre-training domain to downstream tasks. Existing approaches merely leverage contrastive loss to learn instance-level discrimination. However, lack of category information will lead to hard-positive problem that constrains the generalization ability of this kind of methods. We find that the multi-task process of meta learning can provide a solution to this problem. In this paper, we propose a Meta-Contrastive Network (MCN), which combines the contrastive learning and meta learning, to enhance the learning ability of existing self-supervised approaches. Our method contains two training stages based on model-agnostic meta learning (MAML), each of which consists of a contrastive branch and a meta branch. Extensive evaluations demonstrate the effectiveness of our method. For two downstream tasks, i.e., video action recognition and video retrieval, MCN outperforms state-of-the-art approaches on UCF101 and HMDB51 datasets. To be more specific, with R(2+1)D backbone, MCN achieves Top-1 accuracies of 84.8% and 54.5% for video action recognition, as well as 52.5% and 23.7% for video retrieval.
As a challenging task of high-level video understanding, weakly supervised temporal action localization has been attracting increasing attention. With only video annotations, most existing methods seek to handle this task with a localization-by-classification framework, which generally adopts a selector to select snippets of high probabilities of actions or namely the foreground. Nevertheless, the existing foreground selection strategies have a major limitation of only considering the unilateral relation from foreground to actions, which cannot guarantee the foreground-action consistency. In this paper, we present a framework named FAC-Net based on the I3D backbone, on which three branches are appended, named class-wise foreground classification branch, class-agnostic attention branch and multiple instance learning branch. First, our class-wise foreground classification branch regularizes the relation between actions and foreground to maximize the foreground-background separation. Besides, the class-agnostic attention branch and multiple instance learning branch are adopted to regularize the foreground-action consistency and help to learn a meaningful foreground classifier. Within each branch, we introduce a hybrid attention mechanism, which calculates multiple attention scores for each snippet, to focus on both discriminative and less-discriminative snippets to capture the full action boundaries. Experimental results on THUMOS14 and ActivityNet1.3 demonstrate the state-of-the-art performance of our method. Our code is available at https://github.com/LeonHLJ/FAC-Net.
Human action recognition is a well-known computer vision and pattern recognition task of identifying which action a man is actually doing. Extracting the keypoint information of a single human with both spatial and temporal features of action sequences plays an essential role to accomplish the task.In this paper, we propose a human action system for Red-Green-Blue(RGB) input video with our own designed module. Based on the efficient Gated Recurrent Unit(GRU) for spatio-temporal feature extraction, we add another sampling module and normalization module to improve the performance of the model in order to recognize the human actions. Furthermore, we build a novel dataset with a similar background and discriminative actions for both human keypoint prediction and behavior recognition. To get a better result, we retrain the pose model with our new dataset to get better performance. Experimental results demonstrate the effectiveness of the proposed model on our own human behavior recognition dataset and some public datasets.
Weakly-Supervised Temporal Action Localization (WSTAL) aims to localize actions in untrimmed videos with only video-level labels. Currently, most state-of-the-art WSTAL methods follow a Multi-Instance Learning (MIL) pipeline: producing snippet-level predictions first and then aggregating to the video-level prediction. However, we argue that existing methods have overlooked two important drawbacks: 1) inadequate use of motion information and 2) the incompatibility of prevailing cross-entropy training loss. In this paper, we analyze that the motion cues behind the optical flow features are complementary informative. Inspired by this, we propose to build a context-dependent motion prior, termed as motionness. Specifically, a motion graph is introduced to model motionness based on the local motion carrier (e.g., optical flow). In addition, to highlight more informative video snippets, a motion-guided loss is proposed to modulate the network training conditioned on motionness scores. Extensive ablation studies confirm that motionness efficaciously models action-of-interest, and the motion-guided loss leads to more accurate results. Besides, our motion-guided loss is a plug-and-play loss function and is applicable with existing WSTAL methods. Without loss of generality, based on the standard MIL pipeline, our method achieves new state-of-the-art performance on three challenging benchmarks, including THUMOS'14, ActivityNet v1.2 and v1.3.
We tackle the problem of localizing temporal intervals of actions with only a single frame label for each action instance for training. Owing to label sparsity, existing work fails to learn action completeness, resulting in fragmentary action predictions. In this paper, we propose a novel framework, where dense pseudo-labels are generated to provide completeness guidance for the model. Concretely, we first select pseudo background points to supplement point-level action labels. Then, by taking the points as seeds, we search for the optimal sequence that is likely to contain complete action instances while agreeing with the seeds. To learn completeness from the obtained sequence, we introduce two novel losses that contrast action instances with background ones in terms of action score and feature similarity, respectively. Experimental results demonstrate that our completeness guidance indeed helps the model to locate complete action instances, leading to large performance gains especially under high IoU thresholds. Moreover, we demonstrate the superiority of our method over existing state-of-the-art methods on four benchmarks: THUMOS'14, GTEA, BEOID, and ActivityNet. Notably, our method even performs comparably to recent fully-supervised methods, at the 6 times cheaper annotation cost. Our code is available at https://github.com/Pilhyeon.
Temporal Action Localization (TAL) task which is to predict the start and end of each action in a video along with the class label of the action has numerous applications in the real world. But due to the complexity of this task, acceptable accuracy rates have not been achieved yet, whereas this is not the case regarding the action recognition task. In this paper, we propose a new network based on Gated Recurrent Unit (GRU) and two novel post-processing methods for TAL task. Specifically, we propose a new design for the output layer of the conventionally GRU resulting in the so-called GRU-Split network. Moreover, linear interpolation is used to generate the action proposals with precise start and end times. Finally, to rank the generated proposals appropriately, we use a Learn to Rank (LTR) approach. We evaluated the performance of the proposed method on Thumos14 and ActivityNet-1.3 datasets. Results show the superiority of the performance of the proposed method compared to state-of-the-art. Specifically in the mean Average Precision (mAP) metric at Intersection over Union (IoU) of 0.7 on Thumos14, we get 27.52% accuracy which is 5.12% better than that of state-of-the-art methods.
Action recognition is an important task for video understanding with broad applications. However, developing an effective action recognition solution often requires extensive engineering efforts in building and testing different combinations of the modules and their hyperparameters. In this demo, we present AutoVideo, a Python system for automated video action recognition. AutoVideo is featured for 1) highly modular and extendable infrastructure following the standard pipeline language, 2) an exhaustive list of primitives for pipeline construction, 3) data-driven tuners to save the efforts of pipeline tuning, and 4) easy-to-use Graphical User Interface (GUI). AutoVideo is released under MIT license at https://github.com/datamllab/autovideo
Skeleton-based human action recognition has attracted increasing attention in recent years. However, most of the existing works focus on supervised learning which requiring a large number of annotated action sequences that are often expensive to collect. We investigate unsupervised representation learning for skeleton action recognition, and design a novel skeleton cloud colorization technique that is capable of learning skeleton representations from unlabeled skeleton sequence data. Specifically, we represent a skeleton action sequence as a 3D skeleton cloud and colorize each point in the cloud according to its temporal and spatial orders in the original (unannotated) skeleton sequence. Leveraging the colorized skeleton point cloud, we design an auto-encoder framework that can learn spatial-temporal features from the artificial color labels of skeleton joints effectively. We evaluate our skeleton cloud colorization approach with action classifiers trained under different configurations, including unsupervised, semi-supervised and fully-supervised settings. Extensive experiments on NTU RGB+D and NW-UCLA datasets show that the proposed method outperforms existing unsupervised and semi-supervised 3D action recognition methods by large margins, and it achieves competitive performance in supervised 3D action recognition as well.
Effectively tackling the problem of temporal action localization (TAL) necessitates a visual representation that jointly pursues two confounding goals, i.e., fine-grained discrimination for temporal localization and sufficient visual invariance for action classification. We address this challenge by enriching both the local and global contexts in the popular two-stage temporal localization framework, where action proposals are first generated followed by action classification and temporal boundary regression. Our proposed model, dubbed ContextLoc, can be divided into three sub-networks: L-Net, G-Net and P-Net. L-Net enriches the local context via fine-grained modeling of snippet-level features, which is formulated as a query-and-retrieval process. G-Net enriches the global context via higher-level modeling of the video-level representation. In addition, we introduce a novel context adaptation module to adapt the global context to different proposals. P-Net further models the context-aware inter-proposal relations. We explore two existing models to be the P-Net in our experiments. The efficacy of our proposed method is validated by experimental results on the THUMOS14 (54.3\% at [email omitted]) and ActivityNet v1.3 (56.01\% at [email omitted]) datasets, which outperforms recent states of the art. Code is available at https://github.com/buxiangzhiren/ContextLoc.