View while Moving: Efficient Video Recognition in Long-untrimmed Videos

• URL: http://arxiv.org/abs/2308.04834v2
• Date: Wed, 20 Mar 2024 03:07:26 GMT
• Title: View while Moving: Efficient Video Recognition in Long-untrimmed Videos
• Authors: Ye Tian, Mengyu Yang, Lanshan Zhang, Zhizhen Zhang, Yang Liu, Xiaohui Xie, Xirong Que, Wendong Wang,
• Abstract summary: We propose a novel recognition paradigm "View while Moving" for efficient long-untrimmed video recognition. In contrast to the two-stage paradigm, our paradigm only needs to access the raw frame once. Our approach outperforms state-of-the-art methods in terms of accuracy as well as efficiency.
• Score: 17.560160747282147
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent adaptive methods for efficient video recognition mostly follow the two-stage paradigm of "preview-then-recognition" and have achieved great success on multiple video benchmarks. However, this two-stage paradigm involves two visits of raw frames from coarse-grained to fine-grained during inference (cannot be parallelized), and the captured spatiotemporal features cannot be reused in the second stage (due to varying granularity), being not friendly to efficiency and computation optimization. To this end, inspired by human cognition, we propose a novel recognition paradigm of "View while Moving" for efficient long-untrimmed video recognition. In contrast to the two-stage paradigm, our paradigm only needs to access the raw frame once. The two phases of coarse-grained sampling and fine-grained recognition are combined into unified spatiotemporal modeling, showing great performance. Moreover, we investigate the properties of semantic units in video and propose a hierarchical mechanism to efficiently capture and reason about the unit-level and video-level temporal semantics in long-untrimmed videos respectively. Extensive experiments on both long-untrimmed and short-trimmed videos demonstrate that our approach outperforms state-of-the-art methods in terms of accuracy as well as efficiency, yielding new efficiency and accuracy trade-offs for video spatiotemporal modeling.

Related papers

• Zero-Shot Video Translation and Editing with Frame Spatial-Temporal Correspondence [81.82643953694485]
  We present FRESCO, which integrates intra-frame correspondence with inter-frame correspondence to formulate a more robust spatial-temporal constraint.<n>Our method goes beyond attention guidance to explicitly optimize features, achieving high spatial-temporal consistency with the input video.<n>We verify FRESCO adaptations on two zero-shot tasks of video-to-video translation and text-guided video editing.
  arXiv  Detail & Related papers  (2025-12-03T15:51:11Z)
• Back to the Feature: Explaining Video Classifiers with Video Counterfactual Explanations [11.039713164587456]
  Counterfactual explanations (CFEs) are minimal and semantically meaningful modifications of the input of a model that alter the model predictions.<n>For the counterfactual videos to be useful, they have to be physically plausible, temporally coherent, and exhibit smooth motion trajectories.<n>We propose Back To The Feature (BTTF), an optimization framework that generates video CFEs.
  arXiv  Detail & Related papers  (2025-11-25T13:31:30Z)
• SwiftVideo: A Unified Framework for Few-Step Video Generation through Trajectory-Distribution Alignment [76.60024640625478]
  Diffusion-based or flow-based models have achieved significant progress in video synthesis but require multiple iterative sampling steps.<n>We propose a unified and stable distillation framework that combines the advantages of trajectory-preserving and distribution-matching strategies.<n>Our method maintains high-quality video generation while substantially reducing the number of inference steps.
  arXiv  Detail & Related papers  (2025-08-08T07:26:34Z)
• Multimodal Lengthy Videos Retrieval Framework and Evaluation Metric [1.9774761182870912]
  We introduce a unified framework that combines a visual matching stream and an aural matching stream with a unique subtitles-based video segmentation approach. We conduct experiments on the YouCook2 benchmark, showing promising retrieval performance.
  arXiv  Detail & Related papers  (2025-04-06T18:18:09Z)
• Towards Efficient and Effective Text-to-Video Retrieval with Coarse-to-Fine Visual Representation Learning [15.998149438353133]
  We propose a two-stage retrieval architecture for text-to-video retrieval. In training phase, we design a parameter-free text-gated interaction block (TIB) for fine-grained video representation learning. In retrieval phase, we use coarse-grained video representations for fast recall of top-k candidates, which are then reranked by fine-grained video representations.
  arXiv  Detail & Related papers  (2024-01-01T08:54:18Z)
• Multi-Modal Video Topic Segmentation with Dual-Contrastive Domain Adaptation [74.51546366251753]
  Video topic segmentation unveils the coarse-grained semantic structure underlying videos. We introduce a multi-modal video topic segmenter that utilizes both video transcripts and frames. Our proposed solution significantly surpasses baseline methods in terms of both accuracy and transferability.
  arXiv  Detail & Related papers  (2023-11-30T21:59:05Z)
• Revisiting Kernel Temporal Segmentation as an Adaptive Tokenizer for Long-form Video Understanding [57.917616284917756]
  Real-world videos are often several minutes long with semantically consistent segments of variable length. A common approach to process long videos is applying a short-form video model over uniformly sampled clips of fixed temporal length. This approach neglects the underlying nature of long videos since fixed-length clips are often redundant or uninformative.
  arXiv  Detail & Related papers  (2023-09-20T18:13:32Z)
• LocFormer: Enabling Transformers to Perform Temporal Moment Localization on Long Untrimmed Videos With a Feature Sampling Approach [35.93734845932161]
  LocFormer is a Transformer-based model for video grounding that operates at a constant memory footprint regardless of the video length. We propose a modular design that separates functionality, enabling us to learn an inductive bias via supervising the self-attention heads.
  arXiv  Detail & Related papers  (2021-12-19T05:32:14Z)
• ASCNet: Self-supervised Video Representation Learning with Appearance-Speed Consistency [62.38914747727636]
  We study self-supervised video representation learning, which is a challenging task due to 1) a lack of labels for explicit supervision and 2) unstructured and noisy visual information. Existing methods mainly use contrastive loss with video clips as the instances and learn visual representation by discriminating instances from each other. In this paper, we observe that the consistency between positive samples is the key to learn robust video representations.
  arXiv  Detail & Related papers  (2021-06-04T08:44:50Z)
• FrameExit: Conditional Early Exiting for Efficient Video Recognition [11.92976432364216]
  We propose a conditional early exiting framework for efficient video recognition. Our model learns to process fewer frames for simpler videos and more frames for complex ones. Our method sets a new state of the art for efficient video understanding on the HVU benchmark.
  arXiv  Detail & Related papers  (2021-04-27T18:01:05Z)
• Coarse-Fine Networks for Temporal Activity Detection in Videos [45.03545172714305]
  We introduce 'Co-Fine Networks', a two-stream architecture which benefits from different abstractions of temporal resolution to learn better video representations for long-term motion. We show that our method can outperform the state-of-the-arts for action detection in public datasets with a significantly reduced compute and memory footprint.
  arXiv  Detail & Related papers  (2021-03-01T20:48:01Z)
• Semi-Supervised Action Recognition with Temporal Contrastive Learning [50.08957096801457]
  We learn a two-pathway temporal contrastive model using unlabeled videos at two different speeds. We considerably outperform video extensions of sophisticated state-of-the-art semi-supervised image recognition methods.
  arXiv  Detail & Related papers  (2021-02-04T17:28:35Z)
• Depth Guided Adaptive Meta-Fusion Network for Few-shot Video Recognition [86.31412529187243]
  Few-shot video recognition aims at learning new actions with only very few labeled samples. We propose a depth guided Adaptive Meta-Fusion Network for few-shot video recognition which is termed as AMeFu-Net.
  arXiv  Detail & Related papers  (2020-10-20T03:06:20Z)
• Temporal Context Aggregation for Video Retrieval with Contrastive Learning [81.12514007044456]
  We propose TCA, a video representation learning framework that incorporates long-range temporal information between frame-level features. The proposed method shows a significant performance advantage (17% mAP on FIVR-200K) over state-of-the-art methods with video-level features.
  arXiv  Detail & Related papers  (2020-08-04T05:24:20Z)

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.