paper-with-me

홈 › Papers

Sim-DETR: Unlock DETR for Temporal Sentence Grounding

2025-09-28 · Jiajin Tang, Zhengxuan Wei, Yuchen Zhu, Cheng Shi, Guanbin Li, Liang Lin, Sibei Yang arxiv

Temporal sentence grounding aims to identify exact moments in a video that correspond to a given textual query, typically addressed with detection transformer (DETR) solutions. However, we find that typical strategies designed to enhance DETR do not improve, and may even degrade, its performance in this task. We systematically analyze and identify the root causes of this abnormal behavior: (1) conflicts between queries from similar target moments and (2) internal query conflicts due to the tension between global semantics and local localization. Building on these insights, we propose a simple yet powerful baseline, Sim-DETR, which extends the standard DETR with two minor modifications in the decoder layers: (1) constraining self-attention between queries based on their semantic and positional overlap and (2) adding query-to-frame alignment to bridge the global and local contexts. Experiments demonstrate that Sim-DETR unlocks the full potential of DETR for temporal sentence grounding, offering a strong baseline for future research.

📄 PDF Abstract BibTeX arXiv:2509.23867

Code (0)

등록된 구현이 없습니다.

Tasks

Temporal Sentence Grounding

Similar Papers 제목 키워드 기반

Correlation-Guided Query-Dependency Calibration for Video Temporal Grounding

2023-11-15 · WonJun Moon, Sangeek Hyun, SuBeen Lee, Jae-Pil Heo

Temporal Grounding is to identify specific moments or highlights from a video corresponding to textual descriptions. Typical approaches in temporal grounding treat all video clips equally during the encoding process rega…

Highlight DetectionMoment RetrievalNatural Language Moment RetrievalRepresentation Learning+1

BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos

2023-11-30 · Pilhyeon Lee, Hyeran Byun

Temporal sentence grounding aims to localize moments relevant to a language description. Recently, DETR-like approaches achieved notable progress by predicting the center and length of a target moment. However, they suff…

Moment RetrievalNatural Language Moment RetrievalSentenceTemporal Sentence Grounding

TubeDETR: Spatio-Temporal Video Grounding with Transformers

2022-03-30 · CVPR 2022 1 · Antoine Yang, Antoine Miech, Josef Sivic, Ivan Laptev 외

We consider the problem of localizing a spatio-temporal tube in a video corresponding to a given text query. This is a challenging task that requires the joint and efficient modeling of temporal, spatial and multi-modal …

DecoderLanguage-Based Temporal LocalizationNatural Language Visual Groundingobject-detection+6

Augmented 2D-TAN: A Two-stage Approach for Human-centric Spatio-Temporal Video Grounding

2021-06-20 · Chaolei Tan, Zihang Lin, Jian-Fang Hu, Xiang Li 외

We propose an effective two-stage approach to tackle the problem of language-based Human-centric Spatio-Temporal Video Grounding (HC-STVG) task. In the first stage, we propose an Augmented 2D Temporal Adjacent Network (A…

Spatio-Temporal Video GroundingVideo Grounding

Diversifying Query: Region-Guided Transformer for Temporal Sentence Grounding

2024-05-31 · Xiaolong Sun, Liushuai Shi, Le Wang, Sanping Zhou 외

Temporal sentence grounding is a challenging task that aims to localize the moment spans relevant to a language description. Although recent DETR-based models have achieved notable progress by leveraging multiple learnab…

AttributeMoment QueriesSentenceTemporal Sentence Grounding