With rapidly evolving internet technologies and emerging tools, sports related videos generated online are increasing at an unprecedentedly fast pace. To automate sports video editing/highlight generation process, a key task is to precisely recognize and locate the events in the long untrimmed videos. In this tech report, we present a two-stage paradigm to detect what and when events happen in soccer broadcast videos. Specifically, we fine-tune multiple action recognition models on soccer data to extract high-level semantic features, and design a transformer based temporal detection module to locate the target events. This approach achieved the state-of-the-art performance in both two tasks, i.e., action spotting and replay grounding, in the SoccerNet-v2 Challenge, under CVPR 2021 ActivityNet workshop. Our soccer embedding features are released at https://github.com/baidu-research/vidpress-sports. By sharing these features with the broader community, we hope to accelerate the research into soccer video understanding.
The vision community is witnessing a modeling shift from CNNs to Transformers, where pure Transformer architectures have attained top accuracy on the major video recognition benchmarks. These video models are all built on Transformer layers that globally connect patches across the spatial and temporal dimensions. In this paper, we instead advocate an inductive bias of locality in video Transformers, which leads to a better speed-accuracy trade-off compared to previous approaches which compute self-attention globally even with spatial-temporal factorization. The locality of the proposed video architecture is realized by adapting the Swin Transformer designed for the image domain, while continuing to leverage the power of pre-trained image models. Our approach achieves state-of-the-art accuracy on a broad range of video recognition benchmarks, including on action recognition (84.9 top-1 accuracy on Kinetics-400 and 86.1 top-1 accuracy on Kinetics-600 with ~20x less pre-training data and ~3x smaller model size) and temporal modeling (69.6 top-1 accuracy on Something-Something v2). The code and models will be made publicly available at https://github.com/SwinTransformer/Video-Swin-Transformer.
In this paper, we introduce a novel visual representation learning which relies on a handful of adaptively learned tokens, and which is applicable to both image and video understanding tasks. Instead of relying on hand-designed splitting strategies to obtain visual tokens and processing a large number of densely sampled patches for attention, our approach learns to mine important tokens in visual data. This results in efficiently and effectively finding a few important visual tokens and enables modeling of pairwise attention between such tokens, over a longer temporal horizon for videos, or the spatial content in images. Our experiments demonstrate strong performance on several challenging benchmarks for both image and video recognition tasks. Importantly, due to our tokens being adaptive, we accomplish competitive results at significantly reduced compute amount. We obtain comparable results to the state-of-the-arts on ImageNet while being computationally more efficient. We also confirm the effectiveness of the approach on multiple video datasets, including Kinetics-400, Kinetics-600, Charades, and AViD. The code is available at: https://github.com/google-research/scenic/tree/main/scenic/projects/token_learner
Our world offers a never-ending stream of visual stimuli, yet today's vision systems only accurately recognize patterns within a few seconds. These systems understand the present, but fail to contextualize it in past or future events. In this paper, we study long-form video understanding. We introduce a framework for modeling long-form videos and develop evaluation protocols on large-scale datasets. We show that existing state-of-the-art short-term models are limited for long-form tasks. A novel object-centric transformer-based video recognition architecture performs significantly better on 7 diverse tasks. It also outperforms comparable state-of-the-art on the AVA dataset.
Video understanding relies on perceiving the global content and modeling its internal connections (e.g., causality, movement, and spatio-temporal correspondence). To learn these interactions, we apply a mask-then-predict pre-training task on discretized video tokens generated via VQ-VAE. Unlike language, where the text tokens are more independent, neighboring video tokens typically have strong correlations (e.g., consecutive video frames usually look very similar), and hence uniformly masking individual tokens will make the task too trivial to learn useful representations. To deal with this issue, we propose a block-wise masking strategy where we mask neighboring video tokens in both spatial and temporal domains. We also add an augmentation-free contrastive learning method to further capture the global content by predicting whether the video clips are sampled from the same video. We pre-train our model on uncurated videos and show that our pre-trained model can reach state-of-the-art results on several video understanding datasets (e.g., SSV2, Diving48). Lastly, we provide detailed analyses on model scalability and pre-training method design. Code is released at https://github.com/airsplay/vimpac.
Temporal action detection (TAD) aims to determine the semantic label and the temporal interval of every action instance in an untrimmed video. It is a fundamental and challenging task in video understanding. Previous methods tackle this task with complicated pipelines. They often need to train multiple networks and involve hand-designed operations, such as non-maximal suppression and anchor generation, which limit the flexibility and prevent end-to-end learning. In this paper, we propose an end-to-end Transformer-based method for TAD, termed TadTR. Given a small set of learnable embeddings called action queries, TadTR adaptively extracts temporal context information from the video for each query and directly predicts action instances with the context. To adapt Transformer to TAD, we propose three improvements to enhance its locality awareness. The core is a temporal deformable attention module that selectively attends to a sparse set of key snippets in a video. A segment refinement mechanism and an actionness regression head are designed to refine the boundaries and confidence of the predicted instances, respectively. With such a simple pipeline, TadTR requires lower computation cost than previous detectors, while preserving remarkable performance. As a self-contained detector, it achieves state-of-the-art performance on THUMOS14 (56.7% mAP) and HACS Segments (32.09% mAP). Combined with an extra action classifier, it obtains 36.75% mAP on ActivityNet-1.3. Code is available at https://github.com/xlliu7/TadTR.
Video transcript summarization is a fundamental task for video understanding. Conventional approaches for transcript summarization are usually built upon the summarization data for written language such as news articles, while the domain discrepancy may degrade the model performance on spoken text. In this paper, we present VT-SSum, a benchmark dataset with spoken language for video transcript segmentation and summarization, which includes 125K transcript-summary pairs from 9,616 videos. VT-SSum takes advantage of the videos from VideoLectures.NET by leveraging the slides content as the weak supervision to generate the extractive summary for video transcripts. Experiments with a state-of-the-art deep learning approach show that the model trained with VT-SSum brings a significant improvement on the AMI spoken text summarization benchmark. VT-SSum is publicly available at https://github.com/Dod-o/VT-SSum to support the future research of video transcript segmentation and summarization tasks.
With the recent surge in the research of vision transformers, they have demonstrated remarkable potential for various challenging computer vision applications, such as image recognition, point cloud classification as well as video understanding. In this paper, we present empirical results for training a stronger video vision transformer on the EPIC-KITCHENS-100 Action Recognition dataset. Specifically, we explore training techniques for video vision transformers, such as augmentations, resolutions as well as initialization, etc. With our training recipe, a single ViViT model achieves the performance of 47.4\% on the validation set of EPIC-KITCHENS-100 dataset, outperforming what is reported in the original paper by 3.4%. We found that video transformers are especially good at predicting the noun in the verb-noun action prediction task. This makes the overall action prediction accuracy of video transformers notably higher than convolutional ones. Surprisingly, even the best video transformers underperform the convolutional networks on the verb prediction. Therefore, we combine the video vision transformers and some of the convolutional video networks and present our solution to the EPIC-KITCHENS-100 Action Recognition competition.
This technical report extends our work presented in [9] with more experiments. In [9], we tackle long-term video understanding, which requires reasoning from current and past or future observations and raises several fundamental questions. How should temporal or sequential relationships be modelled? What temporal extent of information and context needs to be processed? At what temporal scale should they be derived? [9] addresses these questions with a flexible multi-granular temporal aggregation framework. In this report, we conduct further experiments with this framework on different tasks and a new dataset, EPIC-KITCHENS-100.
Temporal action localization (TAL) is an important and challenging problem in video understanding. However, most existing TAL benchmarks are built upon the coarse granularity of action classes, which exhibits two major limitations in this task. First, coarse-level actions can make the localization models overfit in high-level context information, and ignore the atomic action details in the video. Second, the coarse action classes often lead to the ambiguous annotations of temporal boundaries, which are inappropriate for temporal action localization. To tackle these problems, we develop a novel large-scale and fine-grained video dataset, coined as FineAction, for temporal action localization. In total, FineAction contains 103K temporal instances of 106 action categories, annotated in 17K untrimmed videos. Compared to the existing TAL datasets, our FineAction takes distinct characteristics of fine action classes with rich diversity, dense annotations of multiple instances, and co-occurring actions of different classes, which introduces new opportunities and challenges for temporal action localization. To benchmark FineAction, we systematically investigate the performance of several popular temporal localization methods on it, and deeply analyze the influence of fine-grained instances in temporal action localization. As a minor contribution, we present a simple baseline approach for handling the fine-grained action detection, which achieves an mAP of 13.17% on our FineAction. We believe that FineAction can advance research of temporal action localization and beyond.
We present a simplified, task-agnostic multi-modal pre-training approach that can accept either video or text input, or both for a variety of end tasks. Existing pre-training are task-specific by adopting either a single cross-modal encoder that requires both modalities, limiting their use for retrieval-style end tasks or more complex multitask learning with two unimodal encoders, limiting early cross-modal fusion. We instead introduce new pretraining masking schemes that better mix across modalities (e.g. by forcing masks for text to predict the closest video embeddings) while also maintaining separability (e.g. unimodal predictions are sometimes required, without using all the input). Experimental results show strong performance across a wider range of tasks than any previous methods, often outperforming task-specific pre-training. Code is made available at https://github.com/pytorch/fairseq/tree/main/examples/MMPT.
We introduce NExT-QA, a rigorously designed video question answering (VideoQA) benchmark to advance video understanding from describing to explaining the temporal actions. Based on the dataset, we set up multi-choice and open-ended QA tasks targeting causal action reasoning, temporal action reasoning, and common scene comprehension. Through extensive analysis of baselines and established VideoQA techniques, we find that top-performing methods excel at shallow scene descriptions but are weak in causal and temporal action reasoning. Furthermore, the models that are effective on multi-choice QA, when adapted to open-ended QA, still struggle in generalizing the answers. This raises doubt on the ability of these models to reason and highlights possibilities for improvement. With detailed results for different question types and heuristic observations for future works, we hope NExT-QA will guide the next generation of VQA research to go beyond superficial scene description towards a deeper understanding of videos. (The dataset and related resources are available at https://github.com/doc-doc/NExT-QA.git)
Spatio-temporal action detection is an important and challenging problem in video understanding. The existing action detection benchmarks are limited in aspects of small numbers of instances in a trimmed video or low-level atomic actions. This paper aims to present a new multi-person dataset of spatio-temporal localized sports actions, coined as MultiSports. We first analyze the important ingredients of constructing a realistic and challenging dataset for spatio-temporal action detection by proposing three criteria: (1) multi-person scenes and motion dependent identification, (2) with well-defined boundaries, (3) relatively fine-grained classes of high complexity. Based on these guide-lines, we build the dataset of MultiSports v1.0 by selecting 4 sports classes, collecting 3200 video clips, and annotating 37701 action instances with 902k bounding boxes. Our datasets are characterized with important properties of high diversity, dense annotation, and high quality. Our Multi-Sports, with its realistic setting and detailed annotations, exposes the intrinsic challenges of spatio-temporal action detection. To benchmark this, we adapt several baseline methods to our dataset and give an in-depth analysis on the action detection results in our dataset. We hope our MultiSports can serve as a standard benchmark for spatio-temporal action detection in the future. Our dataset website is at https://deeperaction.github.io/multisports/.
Video understanding calls for a model to learn the characteristic interplay between static scene content and its dynamics: Given an image, the model must be able to predict a future progression of the portrayed scene and, conversely, a video should be explained in terms of its static image content and all the remaining characteristics not present in the initial frame. This naturally suggests a bijective mapping between the video domain and the static content as well as residual information. In contrast to common stochastic image-to-video synthesis, such a model does not merely generate arbitrary videos progressing the initial image. Given this image, it rather provides a one-to-one mapping between the residual vectors and the video with stochastic outcomes when sampling. The approach is naturally implemented using a conditional invertible neural network (cINN) that can explain videos by independently modelling static and other video characteristics, thus laying the basis for controlled video synthesis. Experiments on four diverse video datasets demonstrate the effectiveness of our approach in terms of both the quality and diversity of the synthesized results. Our project page is available at https://bit.ly/3t66bnU.
In this paper, we propose a conditional early exiting framework for efficient video recognition. While existing works focus on selecting a subset of salient frames to reduce the computation costs, we propose to use a simple sampling strategy combined with conditional early exiting to enable efficient recognition. Our model automatically learns to process fewer frames for simpler videos and more frames for complex ones. To achieve this, we employ a cascade of gating modules to automatically determine the earliest point in processing where an inference is sufficiently reliable. We generate on-the-fly supervision signals to the gates to provide a dynamic trade-off between accuracy and computational cost. Our proposed model outperforms competing methods on three large-scale video benchmarks. In particular, on ActivityNet1.3 and mini-kinetics, we outperform the state-of-the-art efficient video recognition methods with 1.3$\times$ and 2.1$\times$ less GFLOPs, respectively. Additionally, our method sets a new state of the art for efficient video understanding on the HVU benchmark.
Video-text retrieval plays an essential role in multi-modal research and has been widely used in many real-world web applications. The CLIP (Contrastive Language-Image Pre-training), an image-language pre-training model, has demonstrated the power of visual concepts learning from web collected image-text datasets. In this paper, we propose a CLIP4Clip model to transfer the knowledge of the CLIP model to video-language retrieval in an end-to-end manner. Several questions are investigated via empirical studies: 1) Whether image feature is enough for video-text retrieval? 2) How a post-pretraining on a large-scale video-text dataset based on the CLIP affect the performance? 3) What is the practical mechanism to model temporal dependency between video frames? And 4) The Hyper-parameters sensitivity of the model on video-text retrieval task. Extensive experimental results present that the CLIP4Clip model transferred from the CLIP can achieve SOTA results on various video-text retrieval datasets, including MSR-VTT, MSVC, LSMDC, ActivityNet, and DiDeMo. We release our code at https://github.com/ArrowLuo/CLIP4Clip.
Modeling temporal visual context across frames is critical for video instance segmentation (VIS) and other video understanding tasks. In this paper, we propose a fast online VIS model named CrossVIS. For temporal information modeling in VIS, we present a novel crossover learning scheme that uses the instance feature in the current frame to pixel-wisely localize the same instance in other frames. Different from previous schemes, crossover learning does not require any additional network parameters for feature enhancement. By integrating with the instance segmentation loss, crossover learning enables efficient cross-frame instance-to-pixel relation learning and brings cost-free improvement during inference. Besides, a global balanced instance embedding branch is proposed for more accurate and more stable online instance association. We conduct extensive experiments on three challenging VIS benchmarks, \ie, YouTube-VIS-2019, OVIS, and YouTube-VIS-2021 to evaluate our methods. To our knowledge, CrossVIS achieves state-of-the-art performance among all online VIS methods and shows a decent trade-off between latency and accuracy. Code will be available to facilitate future research.
We propose fill-in-the-blanks as a video understanding evaluation framework and introduce FIBER -- a novel dataset consisting of 28,000 videos and descriptions in support of this evaluation framework. The fill-in-the-blanks setting tests a model's understanding of a video by requiring it to predict a masked noun phrase in the caption of the video, given the video and the surrounding text. The FIBER benchmark does not share the weaknesses of the current state-of-the-art language-informed video understanding tasks, namely: (1) video question answering using multiple-choice questions, where models perform relatively well because they exploit linguistic biases in the task formulation, thus making our framework challenging for the current state-of-the-art systems to solve; and (2) video captioning, which relies on an open-ended evaluation framework that is often inaccurate because system answers may be perceived as incorrect if they differ in form from the ground truth. The FIBER dataset and our code are available at https://lit.eecs.umich.edu/fiber/.
We propose a new framework for understanding and representing related salient events in a video using visual semantic role labeling. We represent videos as a set of related events, wherein each event consists of a verb and multiple entities that fulfill various roles relevant to that event. To study the challenging task of semantic role labeling in videos or VidSRL, we introduce the VidSitu benchmark, a large-scale video understanding data source with $29K$ $10$-second movie clips richly annotated with a verb and semantic-roles every $2$ seconds. Entities are co-referenced across events within a movie clip and events are connected to each other via event-event relations. Clips in VidSitu are drawn from a large collection of movies (${\sim}3K$) and have been chosen to be both complex (${\sim}4.2$ unique verbs within a video) as well as diverse (${\sim}200$ verbs have more than $100$ annotations each). We provide a comprehensive analysis of the dataset in comparison to other publicly available video understanding benchmarks, several illustrative baselines and evaluate a range of standard video recognition models. Our code and dataset is available at vidsitu.org.
Temporal action localization is an important yet challenging task in video understanding. Typically, such a task aims at inferring both the action category and localization of the start and end frame for each action instance in a long, untrimmed video.While most current models achieve good results by using pre-defined anchors and numerous actionness, such methods could be bothered with both large number of outputs and heavy tuning of locations and sizes corresponding to different anchors. Instead, anchor-free methods is lighter, getting rid of redundant hyper-parameters, but gains few attention. In this paper, we propose the first purely anchor-free temporal localization method, which is both efficient and effective. Our model includes (i) an end-to-end trainable basic predictor, (ii) a saliency-based refinement module to gather more valuable boundary features for each proposal with a novel boundary pooling, and (iii) several consistency constraints to make sure our model can find the accurate boundary given arbitrary proposals. Extensive experiments show that our method beats all anchor-based and actionness-guided methods with a remarkable margin on THUMOS14, achieving state-of-the-art results, and comparable ones on ActivityNet v1.3. Code is available at https://github.com/TencentYoutuResearch/ActionDetection-AFSD.