paper-with-me

Papers

Multi-Granularity Reference-Aided Attentive Feature Aggregation for Video-based Person Re-identification

2020-03-27 · CVPR 2020 6 · Zhizheng Zhang, Cuiling Lan, Wen-Jun Zeng, Zhibo Chen

Video-based person re-identification (reID) aims at matching the same person across video clips. It is a challenging task due to the existence of redundancy among frames, newly revealed appearance, occlusion, and motion blurs. In this paper, we propose an attentive feature aggregation module, namely Multi-Granularity Reference-aided Attentive Feature Aggregation (MG-RAFA), to delicately aggregate spatio-temporal features into a discriminative video-level feature representation. In order to determine the contribution/importance of a spatial-temporal feature node, we propose to learn the attention from a global view with convolutional operations. Specifically, we stack its relations, i.e., pairwise correlations with respect to a representative set of reference feature nodes (S-RFNs) that represents global video information, together with the feature itself to infer the attention. Moreover, to exploit the semantics of different levels, we propose to learn multi-granularity attentions based on the relations captured at different granularities. Extensive ablation studies demonstrate the effectiveness of our attentive feature aggregation module MG-RAFA. Our framework achieves the state-of-the-art performance on three benchmark datasets.

📄 PDF Abstract BibTeX arXiv:2003.12224

Code (0)

등록된 구현이 없습니다.

Tasks

Person Re-IdentificationVideo-Based Person Re-Identification

Similar Papers 제목 키워드 기반

Sandglasset: A Light Multi-Granularity Self-attentive Network For Time-Domain Speech Separation

2021-03-01 · Max W. Y. Lam, Jun Wang, Dan Su, Dong Yu

One of the leading single-channel speech separation (SS) models is based on a TasNet with a dual-path segmentation technique, where the size of each segment remains unchanged throughout all layers. In contrast, our key f…

Computational EfficiencySpeech Separation

LATTE: Lattice ATTentive Encoding for Character-based Word Segmentation

2023-06-01 · Journal of Natural Language Processing 2023 6 · Thodsaporn Chay-intr, Hidetaka Kamigaito, Kotaro Funakoshi, Manabu Okumura

A character sequence comprises at least one or more segmentation alternatives. This can be considered segmentation ambiguity and may weaken segmentation performance in word segmentation. Proper handling of such ambiguity…

Chinese Word SegmentationJapanese Word SegmentationSegmentationThai Word Segmentation

Learning Granularity-Aware Convolutional Neural Network for Fine-Grained Visual Classification

2021-03-04 · Jianwei Song, Ruoyu Yang

Locating discriminative parts plays a key role in fine-grained visual classification due to the high similarities between different objects. Recent works based on convolutional neural networks utilize the feature maps ta…

Fine-Grained Image ClassificationGeneral ClassificationObject

AttentiveChecker: A Bi-Directional Attention Flow Mechanism for Fact Verification

2019-06-01 · NAACL 2019 6 · Santosh Tokala, Vishal G, Avirup Saha, Niloy Ganguly

The recently released FEVER dataset provided benchmark results on a fact-checking task in which given a factual claim, the system must extract textual evidence (sets of sentences from Wikipedia pages) that support or ref…

Claim VerificationFact CheckingFact VerificationRetrieval+1

User Diverse Preference Modeling by Multimodal Attentive Metric Learning

2019-08-21 · Fan Liu, Zhiyong Cheng, Changchang Sun, Yinglong Wang 외

Most existing recommender systems represent a user's preference with a feature vector, which is assumed to be fixed when predicting this user's preferences for different items. However, the same vector cannot accurately …

Metric LearningRecommendation Systems