paper-with-me

Papers

Fine-grained Semantic Alignment Network for Weakly Supervised Temporal Language Grounding

2022-10-21 · Findings (EMNLP) 2021 11 · Yuechen Wang, Wengang Zhou, Houqiang Li

Temporal language grounding (TLG) aims to localize a video segment in an untrimmed video based on a natural language description. To alleviate the expensive cost of manual annotations for temporal boundary labels, we are dedicated to the weakly supervised setting, where only video-level descriptions are provided for training. Most of the existing weakly supervised methods generate a candidate segment set and learn cross-modal alignment through a MIL-based framework. However, the temporal structure of the video as well as the complicated semantics in the sentence are lost during the learning. In this work, we propose a novel candidate-free framework: Fine-grained Semantic Alignment Network (FSAN), for weakly supervised TLG. Instead of view the sentence and candidate moments as a whole, FSAN learns token-by-clip cross-modal semantic alignment by an iterative cross-modal interaction module, generates a fine-grained cross-modal semantic alignment map, and performs grounding directly on top of the map. Extensive experiments are conducted on two widely-used benchmarks: ActivityNet-Captions, and DiDeMo, where our FSAN achieves state-of-the-art performance.

📄 PDF Abstract BibTeX arXiv:2210.11933

Code (0)

등록된 구현이 없습니다.

Tasks

cross-modal alignmentSentence

Similar Papers 제목 키워드 기반

AlignCAT: Visual-Linguistic Alignment of Category and Attribute for Weakly Supervised Visual Grounding

2025-08-05 · Yidan Wang, Chenyi Zhuang, Wutao Liu, Pan Gao 외 arxiv

Weakly supervised visual grounding (VG) aims to locate objects in images based on text descriptions. Despite significant progress, existing methods lack strong cross-modal reasoning to distinguish subtle semantic differe…

Contrastive LearningVisual Grounding

Learning to Tell Apart: Weakly Supervised Video Anomaly Detection via Disentangled Semantic Alignment

2025-11-13 · Wenti Yin, Huaxin Zhang, Xiang Wang, Yuqing Lu 외 arxiv

Recent advancements in weakly-supervised video anomaly detection have achieved remarkable performance by applying the multiple instance learning paradigm based on multimodal foundation models such as CLIP to highlight an…

Weakly-supervised Video Anomaly DetectionMultiple Instance LearningContrastive Learning

Exploring CLIP's Dense Knowledge for Weakly Supervised Semantic Segmentation

2025-03-26 · CVPR 2025 1 · Zhiwei Yang, Yucong Meng, Kexue Fu, Feilong Tang 외

Weakly Supervised Semantic Segmentation (WSSS) with image-level labels aims to achieve pixel-level predictions using Class Activation Maps (CAMs). Recently, Contrastive Language-Image Pre-training (CLIP) has been introdu…

AttributeSemantic SegmentationWeakly supervised Semantic SegmentationWeakly-Supervised Semantic Segmentation

VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detection

2023-08-22 · Peng Wu, Xuerong Zhou, Guansong Pang, Lingru Zhou 외

The recent contrastive language-image pre-training (CLIP) model has shown great success in a wide range of image-level tasks, revealing remarkable ability for learning powerful visual representations with rich semantics.…

Anomaly DetectionBinary ClassificationVideo Anomaly DetectionWeakly-supervised Video Anomaly Detection

Weakly-supervised Object Localization for Few-shot Learning and Fine-grained Few-shot Learning

2020-03-02 · Xiaojian He, Jinfu Lin, Junming Shen

Few-shot learning (FSL) aims to learn novel visual categories from very few samples, which is a challenging problem in real-world applications. Many methods of few-shot classification work well on general images to learn…

ClassificationFew-Shot LearningGeneral ClassificationObject Localization+1