Multi-entity Video Transformers for Fine-Grained Video Representation Learning

• URL: http://arxiv.org/abs/2311.10873v2
• Date: Sun, 22 Jun 2025 18:20:08 GMT
• Title: Multi-entity Video Transformers for Fine-Grained Video Representation Learning
• Authors: Matthew Walmer, Rose Kanjirathinkal, Kai Sheng Tai, Keyur Muzumdar, Taipeng Tian, Abhinav Shrivastava,
• Abstract summary: We re-examine the design of transformer architectures for video representation learning.<n>A key aspect of our approach is the improved sharing of scene information in the temporal pipeline.<n>Our Multi-entity Video Transformer (MV-Former) processes the frames as groups of entities represented as tokens linked across time.
• Score: 34.26732761916984
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The area of temporally fine-grained video representation learning focuses on generating frame-by-frame representations for temporally dense tasks, such as fine-grained action phase classification and frame retrieval. In this work, we advance the state-of-the-art for self-supervised models in this area by re-examining the design of transformer architectures for video representation learning. A key aspect of our approach is the improved sharing of scene information in the temporal pipeline by representing multiple salient entities per frame. Prior works use late-fusion architectures that reduce frames to a single-dimensional vector before modeling any cross-frame dynamics. In contrast, our Multi-entity Video Transformer (MV-Former) processes the frames as groups of entities represented as tokens linked across time. To achieve this, we propose a Learnable Spatial Token Pooling strategy to identify and extract features for multiple salient regions per frame. Through our experiments, we show that MV-Former outperforms previous self-supervised methods, and also surpasses some prior works that use additional supervision or training data. When combined with additional pre-training data from Kinetics-400, MV-Former achieves a further performance boost. Overall, our MV-Former achieves state-of-the-art results on multiple fine-grained video benchmarks and shows that parsing video scenes as collections of entities can enhance performance in video tasks.

Related papers

• Rethinking Video Segmentation with Masked Video Consistency: Did the Model Learn as Intended? [22.191260650245443]
  Video segmentation aims at partitioning video sequences into meaningful segments based on objects or regions of interest within frames. Current video segmentation models are often derived from image segmentation techniques, which struggle to cope with small-scale or class-imbalanced video datasets. We propose a training strategy Masked Video Consistency, which enhances spatial and temporal feature aggregation.
  arXiv  Detail & Related papers  (2024-08-20T08:08:32Z)
• Event-aware Video Corpus Moment Retrieval [79.48249428428802]
  Video Corpus Moment Retrieval (VCMR) is a practical video retrieval task focused on identifying a specific moment within a vast corpus of untrimmed videos. Existing methods for VCMR typically rely on frame-aware video retrieval, calculating similarities between the query and video frames to rank videos. We propose EventFormer, a model that explicitly utilizes events within videos as fundamental units for video retrieval.
  arXiv  Detail & Related papers  (2024-02-21T06:55:20Z)
• Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization [52.63845811751936]
  Video pre-training is challenging due to the modeling of its dynamics video. In this paper, we address such limitations in video pre-training with an efficient video decomposition. Our framework is both capable of comprehending and generating image and video content, as demonstrated by its performance across 13 multimodal benchmarks.
  arXiv  Detail & Related papers  (2024-02-05T16:30:49Z)
• Concatenated Masked Autoencoders as Spatial-Temporal Learner [6.475592804311682]
  We introduce the Concatenated Masked Autoencoders (CatMAE) as a spatial-temporal learner for self-supervised video representation learning. We propose a new data augmentation strategy, Video-Reverse (ViRe), which uses reversed video frames as the model's reconstruction targets.
  arXiv  Detail & Related papers  (2023-11-02T03:08:26Z)
• Multi-grained Temporal Prototype Learning for Few-shot Video Object Segmentation [156.4142424784322]
  Few-Shot Video Object (FSVOS) aims to segment objects in a query video with the same category defined by a few annotated support images. We propose to leverage multi-grained temporal guidance information for handling the temporal correlation nature of video data. Our proposed video IPMT model significantly outperforms previous models on two benchmark datasets.
  arXiv  Detail & Related papers  (2023-09-20T09:16:34Z)
• UMMAFormer: A Universal Multimodal-adaptive Transformer Framework for Temporal Forgery Localization [16.963092523737593]
  We propose a novel framework for temporal forgery localization (TFL) that predicts forgery segments with multimodal adaptation. Our approach achieves state-of-the-art performance on benchmark datasets, including Lav-DF, TVIL, and Psynd.
  arXiv  Detail & Related papers  (2023-08-28T08:20:30Z)
• UnLoc: A Unified Framework for Video Localization Tasks [82.59118972890262]
  UnLoc is a new approach for temporal localization in untrimmed videos. It uses pretrained image and text towers, and feeds tokens to a video-text fusion model. We achieve state of the art results on all three different localization tasks with a unified approach.
  arXiv  Detail & Related papers  (2023-08-21T22:15:20Z)
• Referred by Multi-Modality: A Unified Temporal Transformer for Video Object Segmentation [54.58405154065508]
  We propose a Multi-modal Unified Temporal transformer for Referring video object segmentation. With a unified framework for the first time, MUTR adopts a DETR-style transformer and is capable of segmenting video objects designated by either text or audio reference. For high-level temporal interaction after the transformer, we conduct inter-frame feature communication for different object embeddings, contributing to better object-wise correspondence for tracking along the video.
  arXiv  Detail & Related papers  (2023-05-25T17:59:47Z)
• Multimodal Frame-Scoring Transformer for Video Summarization [4.266320191208304]
  Multimodal Frame-Scoring Transformer (MFST) framework exploiting visual, text and audio features and scoring a video with respect to frames. MFST framework first extracts each modality features (visual-text-audio) using pretrained encoders. MFST trains the multimodal frame-scoring transformer that uses video-text-audio representations as inputs and predicts frame-level scores.
  arXiv  Detail & Related papers  (2022-07-05T05:14:15Z)
• Learning Trajectory-Aware Transformer for Video Super-Resolution [50.49396123016185]
  Video super-resolution aims to restore a sequence of high-resolution (HR) frames from their low-resolution (LR) counterparts. Existing approaches usually align and aggregate video frames from limited adjacent frames. We propose a novel Transformer for Video Super-Resolution (TTVSR)
  arXiv  Detail & Related papers  (2022-04-08T03:37:39Z)
• Self-supervised Video-centralised Transformer for Video Face Clustering [58.12996668434134]
  This paper presents a novel method for face clustering in videos using a video-centralised transformer. We release the first large-scale egocentric video face clustering dataset named EasyCom-Clustering.
  arXiv  Detail & Related papers  (2022-03-24T16:38:54Z)
• VRT: A Video Restoration Transformer [126.79589717404863]
  Video restoration (e.g., video super-resolution) aims to restore high-quality frames from low-quality frames. We propose a Video Restoration Transformer (VRT) with parallel frame prediction and long-range temporal dependency modelling abilities.
  arXiv  Detail & Related papers  (2022-01-28T17:54:43Z)
• Leveraging Local Temporal Information for Multimodal Scene Classification [9.548744259567837]
  Video scene classification models should capture the spatial (pixel-wise) and temporal (frame-wise) characteristics of a video effectively. Transformer models with self-attention which are designed to get contextualized representations for individual tokens given a sequence of tokens, are becoming increasingly popular in many computer vision tasks. We propose a novel self-attention block that leverages both local and global temporal relationships between the video frames to obtain better contextualized representations for the individual frames.
  arXiv  Detail & Related papers  (2021-10-26T19:58:32Z)
• Hierarchical Multimodal Transformer to Summarize Videos [103.47766795086206]
  Motivated by the great success of transformer and the natural structure of video (frame-shot-video), a hierarchical transformer is developed for video summarization. To integrate the two kinds of information, they are encoded in a two-stream scheme, and a multimodal fusion mechanism is developed based on the hierarchical transformer. Practically, extensive experiments show that HMT surpasses most of the traditional, RNN-based and attention-based video summarization methods.
  arXiv  Detail & Related papers  (2021-09-22T07:38:59Z)
• End-to-End Video Instance Segmentation with Transformers [84.17794705045333]
  Video instance segmentation (VIS) is the task that requires simultaneously classifying, segmenting and tracking object instances of interest in video. Here, we propose a new video instance segmentation framework built upon Transformers, termed VisTR, which views the VIS task as a direct end-to-end parallel sequence decoding/prediction problem. For the first time, we demonstrate a much simpler and faster video instance segmentation framework built upon Transformers, achieving competitive accuracy.
  arXiv  Detail & Related papers  (2020-11-30T02:03:50Z)
• Hierarchical Attention Network for Action Segmentation [45.19890687786009]
  The temporal segmentation of events is an essential task and a precursor for the automatic recognition of human actions in the video. We propose a complete end-to-end supervised learning approach that can better learn relationships between actions over time. We evaluate our system on challenging public benchmark datasets, including MERL Shopping, 50 salads, and Georgia Tech Egocentric datasets.
  arXiv  Detail & Related papers  (2020-05-07T02:39:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.