Transformer achieves remarkable successes in understanding 1 and 2-dimensional signals (e.g., NLP and Image Content Understanding). As a potential alternative to convolutional neural networks, it shares merits of strong interpretability, high discriminative power on hyper-scale data, and flexibility in processing varying length inputs. However, its encoders naturally contain computational intensive operations such as pair-wise self-attention, incurring heavy computational burden when being applied on the complex 3-dimensional video signals.
This paper presents Token Shift Module (i.e., TokShift), a novel, zero-parameter, zero-FLOPs operator, for modeling temporal relations within each transformer encoder. Specifically, the TokShift barely temporally shifts partial [Class] token features back-and-forth across adjacent frames. Then, we densely plug the module into each encoder of a plain 2D vision transformer for learning 3D video representation. It is worth noticing that our TokShift transformer is a pure convolutional-free video transformer pilot with computational efficiency for video understanding. Experiments on standard benchmarks verify its robustness, effectiveness, and efficiency. Particularly, with input clips of 8/12 frames, the TokShift transformer achieves SOTA precision: 79.83%/80.40% on the Kinetics-400, 66.56% on EGTEA-Gaze+, and 96.80% on UCF-101 datasets, comparable or better than existing SOTA convolutional counterparts. Our code is open-sourced in: https://github.com/VideoNetworks/TokShift-Transformer.
Pure vision transformer architectures are highly effective for short video classification and action recognition tasks. However, due to the quadratic complexity of self attention and lack of inductive bias, transformers are resource intensive and suffer from data inefficiencies. Long form video understanding tasks amplify data and memory efficiency problems in transformers making current approaches unfeasible to implement on data or memory restricted domains. This paper introduces an efficient Spatio-Temporal Attention Network (STAN) which uses a two-stream transformer architecture to model de…
Video question answering is a challenging task that requires understanding jointly the language input, the visual information in individual video frames, as well as the temporal information about the events occurring in the video. In this paper, we propose a novel multi-stream video encoder for video question answering that uses multiple video inputs and a new video-text iterative co-tokenization approach to answer a variety of questions related to videos. We experimentally evaluate the model on several datasets, such as MSRVTT-QA, MSVD-QA, IVQA, outperforming the previous state-of-the-art by …
Universidad de Los Andes（洛斯安第斯大学）；Google Research（谷歌研究院）
We implemented Video Swin Transformer as a base architecture for the tasks of Point-of-No-Return temporal localization and Object State Change Classification. Our method achieved competitive performance on both challenges.
Video-KTR: Reinforcing Video Reasoning via Key Token Attribution
ByteDance（字节跳动）；School of Electrical and Electronic Engineering, Nanyang Technological University（南洋理工大学电子与电气工程学院）；National University of Singapore（国立新加坡大学）；College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）
A great challenge in video-language (VidL) modeling lies in the disconnection between fixed video representations extracted from image/video understanding models and downstream VidL data. Recent studies try to mitigate this disconnection via end-to-end training. To make it computationally feasible, prior works tend to "imagify" video inputs, i.e., a handful of sparsely sampled frames are fed into a 2D CNN, followed by a simple mean-pooling or concatenation to obtain the overall video representations. Although achieving promising results, such simple approaches may lose temporal information tha…
School of Computer Science, Peking University（北京大学计算机学院）；Beijing Academy of Artificial Intelligence（北京人工智能研究院）；University of California, San Diego（加利福尼亚大学圣迭戈分校）；Renmin University of China（中国人民大学）
University of Melbourne（墨尔本大学）；Monash University（莫纳什大学）；Tsinghua University（清华大学）
Video summarization aims to automatically generate a summary (storyboard or video skim) of a video, which can facilitate large-scale video retrieval and browsing. Most of the existing methods perform video summarization on individual videos, which neglects the correlations among similar videos. Such correlations, however, are also informative for video understanding and video summarization. To address this limitation, we propose Video Joint Modelling based on Hierarchical Transformer (VJMHT) for co-summarization, which takes into consideration the semantic dependencies across videos. Specifica…
National University of Singapore（新加坡国立大学）；Huazhong University of Science and Technology（华中科技大学）；Tsinghua University（清华大学）；Alibaba Group（阿里巴巴集团）
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 perfo…
Midea Group, AI Innovation Center（美的集团人工智能创新中心）；Tongji University（同济大学）
The vision transformer splits each image into a sequence of tokens with fixed length and processes the tokens in the same way as words in natural language processing. More tokens normally lead to better performance but considerably increased computational cost. Motivated by the proverb "A picture is worth a thousand words" we aim to accelerate the ViT model by making a long image short. To this end, we propose a novel approach to assign token length adaptively during inference. Specifically, we first train a ViT model, called Resizable-ViT (ReViT), that can process any given input with diverse…
In learning action recognition, models are typically pre-trained on object recognition with images, such as ImageNet, and later fine-tuned on target action recognition with videos. This approach has achieved good empirical performance especially with recent transformer-based video architectures. While recently many works aim to design more advanced transformer architectures for action recognition, less effort has been made on how to train video transformers. In this work, we explore several training paradigms and present two findings. First, video transformers benefit from joint training on di…
Google Research（谷歌研究院）；Stony Brook University（石溪大学）
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 th…
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 …
Sea AI Lab（Sea人工智能实验室）；Sea-NExT Joint Lab（Sea-NExT联合实验室）；National University of Singapore（新加坡国立大学）
This paper proposes a Video Graph Transformer (VGT) model for Video Quetion Answering (VideoQA). VGT's uniqueness are two-fold: 1) it designs a dynamic graph transformer module which encodes video by explicitly capturing the visual objects, their relations, and dynamics for complex spatio-temporal reasoning; and 2) it exploits disentangled video and text Transformers for relevance comparison between the video and text to perform QA, instead of entangled cross-modal Transformer for answer classification. Vision-text communication is done by additional cross-modal interaction modules. With more …
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 is…
CoVisco: Codec-Native Vision Encoder with Native Token Compression for Unified Image-Video Understanding
ERNIE Team, Baidu Inc.（百度公司ERNIE团队）；The Hong Kong University of Science and Technology（香港科技大学）；Institute of Automation, Chinese Academy of Sciences (CASIA)（中国科学院自动化研究所）
Efficient video action recognition remains a challenging problem. One large model after another takes the place of the state-of-the-art on the Kinetics dataset, but real-world efficiency evaluations are often lacking. In this work, we fill this gap and investigate the use of transformers for efficient action recognition. We propose a novel, lightweight action recognition architecture, VideoLightFormer. In a factorized fashion, we carefully extend the 2D convolutional Temporal Segment Network with transformers, while maintaining spatial and temporal video structure throughout the entire model. …
ViGT: Proposal-free Video Grounding with Learnable Token in Transformer
Hefei University of Technology（合肥工业大学）；Key Laboratory of Knowledge Engineering with Big Data, Ministry of Education（教育部大数据知识工程重点实验室）；Intelligent Interconnected Systems Laboratory of Anhui Province（安徽省智能互联系统实验室）；Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（合肥综合性国家科学中心人工智能研究院）
Compared with the vanilla transformer, the window-based transformer offers a better trade-off between accuracy and efficiency. Although the window-based transformer has made great progress, its long-range modeling capabilities are limited due to the size of the local window and the window connection scheme. To address this problem, we propose a novel Token Transformer (TT). The core mechanism of TT is the addition of a Class (CLS) token for summarizing window information in each local window. We refer to this type of token interaction as CLS Attention. These CLS tokens will interact spatially …
Text-Video retrieval is a task of great practical value and has received increasing attention, among which learning spatial-temporal video representation is one of the research hotspots. The video encoders in the state-of-the-art video retrieval models usually directly adopt the pre-trained vision backbones with the network structure fixed, they therefore can not be further improved to produce the fine-grained spatial-temporal video representation. In this paper, we propose Token Shift and Selection Network (TS2-Net), a novel token shift and selection transformer architecture, which dynamicall…
The Chinese University of Hong Kong（香港中文大学）；Amazon AI（亚马逊人工智能部门）
The architecture of transformers, which recently witness booming applications in vision tasks, has pivoted against the widespread convolutional paradigm. Relying on the tokenization process that splits inputs into multiple tokens, transformers are capable of extracting their pairwise relationships using self-attention. While being the stemming building block of transformers, what makes for a good tokenizer has not been well understood in computer vision. In this work, we investigate this uncharted problem from an information trade-off perspective. In addition to unifying and understanding exis…
Mixup is a commonly adopted data augmentation technique for image classification. Recent advances in mixup methods primarily focus on mixing based on saliency. However, many saliency detectors require intense computation and are especially burdensome for parameter-heavy transformer models. To this end, we propose TokenMixup, an efficient attention-guided token-level data augmentation method that aims to maximize the saliency of a mixed set of tokens. TokenMixup provides x15 faster saliency-aware data augmentation compared to gradient-based methods. Moreover, we introduce a variant of TokenMixu…
