paper-with-me

홈 › Papers

HERO: Hierarchical Embedding-Refinement for Open-Vocabulary Temporal Sentence Grounding in Videos

2026-03-06 · Tingting Han, Xinsong Tao, Yufei Yin, Min Tan, Sicheng Zhao, Zhou Yu arxiv

Temporal Sentence Grounding in Videos (TSGV) aims to temporally localize segments of a video that correspond to a given natural language query. Despite recent progress, most existing TSGV approaches operate under closed-vocabulary settings, limiting their ability to generalize to real-world queries involving novel or diverse linguistic expressions. To bridge this critical gap, we introduce the Open-Vocabulary TSGV (OV-TSGV) task and construct the first dedicated benchmarks--Charades-OV and ActivityNet-OV--that simulate realistic vocabulary shifts and paraphrastic variations. These benchmarks facilitate systematic evaluation of model generalization beyond seen training concepts. To tackle OV-TSGV, we propose HERO(Hierarchical Embedding-Refinement for Open-Vocabulary grounding), a unified framework that leverages hierarchical linguistic embeddings and performs parallel cross-modal refinement. HERO jointly models multi-level semantics and enhances video-language alignment via semantic-guided visual filtering and contrastive masked text refinement. Extensive experiments on both standard and open vocabulary benchmarks demonstrate that HERO consistently surpasses state-of-the-art methods, particularly under open-vocabulary scenarios, validating its strong generalization capability and underscoring the significance of OV-TSGV as a new research direction.

📄 PDF Abstract BibTeX arXiv:2603.06732

Code (0)

등록된 구현이 없습니다.

Tasks

Temporal Sentence Grounding

Similar Papers 제목 키워드 기반

Selective Disclosure Watermarking for Large Language Models

2026-07-06 · Xuyang Chen, Xiang Li, Yangxinyu Xie, Qi Long arxiv

Watermarking methods embed imperceptible and verifiable signals into text generated by large language models (LLMs). Existing approaches include zero-bit schemes for distinguishing synthetic text from human writing and m…

Semantic Alignment in Hyperbolic Space for Open-Vocabulary Semantic Segmentation

2026-05-09 · Hoang M. Truong, Hai Nguyen-Truong, Dang Huynh arxiv

Open-vocabulary semantic segmentation requires adapting image-level vision-language models such as CLIP to dense pixel-level prediction, which is challenging due to the mismatch between hierarchical structure and semanti…

Semantic Segmentation

From SWE-ZERO to SWE-HERO: Execution-free to Execution-based Fine-tuning for Software Engineering Agents

2026-04-02 · Nikolai Ludwig, Wasi Uddin Ahmad, Somshubra Majumdar, Boris Ginsburg arxiv

We introduce SWE-ZERO to SWE-HERO, a two-stage SFT recipe that achieves state-of-the-art results on SWE-bench by distilling open-weight frontier LLMs. Our pipeline replaces resource-heavy dependencies with an evolutionar…

Open-SAT: LLM-Guided Query Embedding Refinement for Open-Vocabulary Object Retrieval in Satellite Imagery

2026-05-06 · Md Adnan Arefeen, Biplob Debnath, Ravi K. Rajendran, Murugan Sankaradas 외 arxiv

In satellite applications, user queries often take the form of open-ended natural language, extending beyond a fixed set of predefined categories. This open-vocabulary nature poses significant challenges for retrieving r…

Image Retrieval

Beyond Isolated Objects: Relationship-aware Open Vocabulary Scene Understanding via 3D Scene Graph Analysis

2026-07-06 · Xianhao Chen, Jiarui Hu, Yuanbo Yang, Xiyu Zhang 외 arxiv

Open-vocabulary 3D scene understanding aims to segment 3D scenes beyond predefined categories by transferring semantic knowledge from vision-language models. Existing methods have advanced this task by lifting language-a…

Scene Understanding