SViTT: Temporal Learning of Sparse Video-Text Transformers

• URL: http://arxiv.org/abs/2304.08809v1
• Date: Tue, 18 Apr 2023 08:17:58 GMT
• Title: SViTT: Temporal Learning of Sparse Video-Text Transformers
• Authors: Yi Li, Kyle Min, Subarna Tripathi, Nuno Vasconcelos
• Abstract summary: We propose SViTT, a sparse video-text architecture that performs multi-frame reasoning with significantly lower cost than naive transformers with dense attention. SViTT employs two forms of sparsity: edge sparsity that limits the query-key communications between tokens in self-attention, and sparsity that discards uninformative visual tokens.
• Score: 65.93031164906812
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Do video-text transformers learn to model temporal relationships across frames? Despite their immense capacity and the abundance of multimodal training data, recent work has revealed the strong tendency of video-text models towards frame-based spatial representations, while temporal reasoning remains largely unsolved. In this work, we identify several key challenges in temporal learning of video-text transformers: the spatiotemporal trade-off from limited network size; the curse of dimensionality for multi-frame modeling; and the diminishing returns of semantic information by extending clip length. Guided by these findings, we propose SViTT, a sparse video-text architecture that performs multi-frame reasoning with significantly lower cost than naive transformers with dense attention. Analogous to graph-based networks, SViTT employs two forms of sparsity: edge sparsity that limits the query-key communications between tokens in self-attention, and node sparsity that discards uninformative visual tokens. Trained with a curriculum which increases model sparsity with the clip length, SViTT outperforms dense transformer baselines on multiple video-text retrieval and question answering benchmarks, with a fraction of computational cost. Project page: http://svcl.ucsd.edu/projects/svitt.

Related papers

• FancyVideo: Towards Dynamic and Consistent Video Generation via Cross-frame Textual Guidance [47.88160253507823]
  We introduce FancyVideo, an innovative video generator that improves the existing text-control mechanism. CTGM incorporates the Temporal Information (TII), Temporal Affinity Refiner (TAR), and Temporal Feature Booster (TFB) at the beginning, middle, and end of cross-attention.
  arXiv  Detail & Related papers  (2024-08-15T14:47:44Z)
• TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding [20.16000249533665]
  TESTA condenses video semantics by adaptively aggregating similar frames, as well as similar patches within each frame. Building upon TESTA, we introduce a pre-trained video-language model equipped with a divided space-time token aggregation module in each video block. We evaluate our model on five datasets for paragraph-to-video retrieval and long-form VideoQA tasks.
  arXiv  Detail & Related papers  (2023-10-29T16:25:32Z)
• Towards Smooth Video Composition [59.134911550142455]
  Video generation requires consistent and persistent frames with dynamic content over time. This work investigates modeling the temporal relations for composing video with arbitrary length, from a few frames to even infinite, using generative adversarial networks (GANs) We show that the alias-free operation for single image generation, together with adequately pre-learned knowledge, brings a smooth frame transition without compromising the per-frame quality.
  arXiv  Detail & Related papers  (2022-12-14T18:54:13Z)
• Temporally Consistent Transformers for Video Generation [80.45230642225913]
  To generate accurate videos, algorithms have to understand the spatial and temporal dependencies in the world. No established benchmarks on complex data exist for rigorously evaluating video generation with long temporal dependencies. We introduce the Temporally Consistent Transformer (TECO), a generative model that substantially improves long-term consistency while also reducing sampling time.
  arXiv  Detail & Related papers  (2022-10-05T17:15:10Z)
• 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)
• Video Transformers: A Survey [42.314208650554264]
  We study the contributions and trends for adapting Transformers to model video data. Specifically, we delve into how videos are embedded and tokenized, finding a very widspread use of large CNN backbones. Also, we analyse the self-supervised losses used to train Video Transformers, which to date are mostly constrained to contrastive approaches.
  arXiv  Detail & Related papers  (2022-01-16T07:31:55Z)
• VIOLET : End-to-End Video-Language Transformers with Masked Visual-token Modeling [88.30109041658618]
  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. We present VIOLET, a fully end-to-end VIdeO-LanguagE Transformer, which adopts a video transformer to explicitly model the temporal dynamics of video inputs.
  arXiv  Detail & Related papers  (2021-11-24T18:31:20Z)
• Long-Short Temporal Contrastive Learning of Video Transformers [62.71874976426988]
  Self-supervised pretraining of video transformers on video-only datasets can lead to action recognition results on par or better than those obtained with supervised pretraining on large-scale image datasets. Our approach, named Long-Short Temporal Contrastive Learning, enables video transformers to learn an effective clip-level representation by predicting temporal context captured from a longer temporal extent.
  arXiv  Detail & Related papers  (2021-06-17T02:30:26Z)

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.