Chengxin Liu

6 papers · 2019–2026 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (14) 🐣 Hot Topic Early Bird

Venues

CVPR (3) ICCV (2) ECCV (1)

Top co-authors

Hao Lu (4) Zhiguo Cao (4) Chenshuang Zhang (2) Tae-Hyun Oh (2) Min Shi (1) Kewei Wang (1) Haipeng Xiong (1) Liang Liu (1) Kyeong Seon Kim (1) Ziming Zhang (1)

Research topics

Artificial Intelligence (4) Computer Vision (4) Core AI (4) Machine Learning (3) Analysis (3) Core Methods (2) Deep Learning (1) Applications (1) Learning Types · Deep Learning (1) Learning Types · Machine Learning (1)

Keywords

object detection (2) crowd counting (2) feature representation (1) temporal alignment (1) vision-language model (1) object hallucination (1) open-set recognition (1) visual token (1) visual feature (1) point query (1) information flow (1) similarity metric (1) class-agnostic counting (1) visual counting (1) hallucination benchmark (1) bilinear matching (1) spatial divide-and-conquer (1) token dynamics (1) audio-visual large language model (1) speech-vision hallucination (1)

Papers

Aligning What Vision-Language Models See and Perceive with Adaptive Information Flow CVPR 2026 SVHalluc: Benchmarking Speech-Vision Hallucination in Audio-Visual Large Language Models CVPR 2026 Point-Query Quadtree for Crowd Counting, Localization, and More ICCV 2023 Represent, Compare, and Learn: A Similarity-Aware Framework for Class-Agnostic Counting CVPR 2022 Robust Object Detection with Inaccurate Bounding Boxes ECCV 2022 From Open Set to Closed Set: Counting Objects by Spatial Divide-and-Conquer ICCV 2019