LTCA: Long-range Temporal Context Attention for Referring Video Object Segmentation

• URL: http://arxiv.org/abs/2510.08305v1
• Date: Thu, 09 Oct 2025 14:55:52 GMT
• Title: LTCA: Long-range Temporal Context Attention for Referring Video Object Segmentation
• Authors: Cilin Yan, Jingyun Wang, Guoliang Kang,
• Abstract summary: We propose an effective long-range temporal context attention (LTCA) mechanism to aggregate global context information into object features.<n>We show our method achieves new state-of-the-art on four referring video segmentation benchmarks.
• Score: 14.277537679679101
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Referring Video Segmentation (RVOS) aims to segment objects in videos given linguistic expressions. The key to solving RVOS is to extract long-range temporal context information from the interactions of expressions and videos to depict the dynamic attributes of each object. Previous works either adopt attention across all the frames or stack dense local attention to achieve a global view of temporal context. However, they fail to strike a good balance between locality and globality, and the computation complexity significantly increases with the increase of video length. In this paper, we propose an effective long-range temporal context attention (LTCA) mechanism to aggregate global context information into object features. Specifically, we aggregate the global context information from two aspects. Firstly, we stack sparse local attentions to balance the locality and globality. We design a dilated window attention across frames to aggregate local context information and perform such attention in a stack of layers to enable a global view. Further, we enable each query to attend to a small group of keys randomly selected from a global pool to enhance the globality. Secondly, we design a global query to interact with all the other queries to directly encode the global context information. Experiments show our method achieves new state-of-the-art on four referring video segmentation benchmarks. Notably, our method shows an improvement of 11.3% and 8.3% on the MeViS valu and val datasets respectively.

Related papers

• Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models [61.11154533305096]
  Video Large Language Models (VLLMs) demonstrate strong video understanding but suffer from inefficiency due to redundant visual tokens.<n>We propose a new perspective that elaborates token textbfAnchors within intra-frame and inter-frame contexts.<n>Our proposed AOT obtains competitive performances across various short- and long-video benchmarks on leading video LLMs.
  arXiv  Detail & Related papers  (2026-03-02T03:06:40Z)
• Temporal Collection and Distribution for Referring Video Object Segmentation [14.886278504056063]
  Referring video object segmentation aims to segment a referent throughout a video sequence according to a natural language expression. We propose to simultaneously maintain a global referent token and a sequence of object queries. We show that our method outperforms state-of-the-art methods on all benchmarks consistently and significantly.
  arXiv  Detail & Related papers  (2023-09-07T04:22:02Z)
• Exploring Intra- and Inter-Video Relation for Surgical Semantic Scene Segmentation [58.74791043631219]
  We propose a novel framework STswinCL that explores the complementary intra- and inter-video relations to boost segmentation performance. We extensively validate our approach on two public surgical video benchmarks, including EndoVis18 Challenge and CaDIS dataset. Experimental results demonstrate the promising performance of our method, which consistently exceeds previous state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-03-29T05:52:23Z)
• Local-Global Context Aware Transformer for Language-Guided Video Segmentation [103.35509224722097]
  We explore the task of language-guided video segmentation (LVS) We present Locater, which augments the Transformer architecture with a finite memory so as to query the entire video with the language expression in an efficient manner. To thoroughly examine the visual grounding capability of LVS models, we contribute a new LVS dataset, A2D-S+, which is built upon A2D-S dataset.
  arXiv  Detail & Related papers  (2022-03-18T07:35:26Z)
• Context-aware Biaffine Localizing Network for Temporal Sentence Grounding [61.18824806906945]
  This paper addresses the problem of temporal sentence grounding (TSG) TSG aims to identify the temporal boundary of a specific segment from an untrimmed video by a sentence query. We propose a novel localization framework that scores all pairs of start and end indices within the video simultaneously with a biaffine mechanism.
  arXiv  Detail & Related papers  (2021-03-22T03:13:05Z)
• Global Context Aware RCNN for Object Detection [1.1939762265857436]
  We propose a novel end-to-end trainable framework, called Global Context Aware (GCA) RCNN. The core component of GCA framework is a context aware mechanism, in which both global feature pyramid and attention strategies are used for feature extraction and feature refinement. In the end, we also present a lightweight version of our method, which only slightly increases model complexity and computational burden.
  arXiv  Detail & Related papers  (2020-12-04T14:56:46Z)
• Local-Global Video-Text Interactions for Temporal Grounding [77.5114709695216]
  This paper addresses the problem of text-to-video temporal grounding, which aims to identify the time interval in a video semantically relevant to a text query. We tackle this problem using a novel regression-based model that learns to extract a collection of mid-level features for semantic phrases in a text query. The proposed method effectively predicts the target time interval by exploiting contextual information from local to global.
  arXiv  Detail & Related papers  (2020-04-16T08:10:41Z)
• Memory Enhanced Global-Local Aggregation for Video Object Detection [33.624831537299734]
  We argue that there are two important cues for humans to recognize objects in videos: the global semantic information and the local localization information. We introduce memory enhanced global-local aggregation (MEGA) network. Our method achieves state-of-the-art performance on ImageNet VID dataset.
  arXiv  Detail & Related papers  (2020-03-26T17:59:38Z)
• See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networks [184.4379622593225]
  We introduce a novel network, called CO-attention Siamese Network (COSNet), to address the unsupervised video object segmentation task. We emphasize the importance of inherent correlation among video frames and incorporate a global co-attention mechanism. We propose a unified and end-to-end trainable framework where different co-attention variants can be derived for mining the rich context within videos.
  arXiv  Detail & Related papers  (2020-01-19T11:10:39Z)

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.