| CARVIEW |
Select Language
HTTP/2 301
server: GitHub.com
content-type: text/html
location: https://www.chengao.vision/iCAN
x-github-request-id: AB9A:15317B:7DDE84:8D1CDF:695168C8
accept-ranges: bytes
age: 0
date: Sun, 28 Dec 2025 17:28:41 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210051-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1766942922.668796,VS0,VE196
vary: Accept-Encoding
x-fastly-request-id: e4ddaf9a36311eee5e97c25878c64f386bc02288
content-length: 162
HTTP/1.1 301 Moved Permanently
Connection: keep-alive
Content-Length: 162
Server: GitHub.com
Content-Type: text/html
Location: https://www.chengao.vision/iCAN/
X-GitHub-Request-Id: F252:272D88:7E5606:8D92AD:695168C7
Accept-Ranges: bytes
Age: 0
Date: Sun, 28 Dec 2025 17:28:42 GMT
Via: 1.1 varnish
X-Served-By: cache-bom-vanm7210080-BOM
X-Cache: MISS
X-Cache-Hits: 0
X-Timer: S1766942922.921283,VS0,VE198
Vary: Accept-Encoding
X-Fastly-Request-ID: 211dce14ac0a41f1f100dee3ac8407d160a77bdb
HTTP/1.1 200 OK
Connection: keep-alive
Content-Length: 3231
Server: GitHub.com
Content-Type: text/html; charset=utf-8
Last-Modified: Wed, 23 Oct 2019 18:49:44 GMT
Access-Control-Allow-Origin: *
ETag: W/"5db0a0c8-2bcb"
expires: Sun, 28 Dec 2025 17:38:42 GMT
Cache-Control: max-age=600
Content-Encoding: gzip
x-proxy-cache: MISS
X-GitHub-Request-Id: 27B0:3157C7:7CD804:8C162F:695168C9
Accept-Ranges: bytes
Age: 0
Date: Sun, 28 Dec 2025 17:28:42 GMT
Via: 1.1 varnish
X-Served-By: cache-bom-vanm7210080-BOM
X-Cache: MISS
X-Cache-Hits: 0
X-Timer: S1766942922.132191,VS0,VE215
Vary: Accept-Encoding
X-Fastly-Request-ID: 0888a2eec9504a93f2c4d31c3849e2c2cd091f08
iCAN
iCAN: Instance-Centric Attention Network
iCAN: Instance-Centric Attention Network
for Human-Object Interaction Detection
Abstract
Recent years have witnessed rapid progress in detecting and recognizing individual object instances. To understand the situation in a scene, however, computers need to recognize how humans interact with surrounding objects. In this paper, we tackle the challenging task of detecting human-object interactions (HOI). Our core idea is that the appearance of a person or an object instance contains informative cues on which relevant parts of an image to attend to for facilitating interaction prediction. To exploit this cue, we propose an instance-centric attention module that learns to dynamically highlight regions in an image conditioned on the appearance of each instance. Such an attention-based network allows us to selectively aggregate features relevant for recognizing HOIs.
We validate the efficacy of the proposed network on the Verb in COCO and HICO-DET datasets and show that our approach compares favorably with the state-of-the-arts.
Paper
BMVC 2018
Supplementary material
Citation
Chen Gao, Yuliang Zou, Jia-Bin Huang, "iCAN: Instance-Centric Attention Network for Human-Object Interaction Detection", in British Machine Vision Conference, 2018.
Bibtex
@inproceedings{gao2018ican,
author = {Gao, Chen and Zou, Yuliang and Huang, Jia-Bin},
title = {iCAN: Instance-Centric Attention Network for Human-Object Interaction Detection},
booktitle = {British Machine Vision Conference},
year = {2018}
}
Network Architecture
Overview
iCAN module
Results
References
- • Yu-Wei Chao, Yunfan Liu, Xieyang Liu, Huayi Zeng, and Jia Deng, “Learning to Detect Human-Object Interactions”, In WACV, 2018.
- • Georgia Gkioxari, Ross Girshick, Piotr Dollár, and Kaiming He, “Detecting and Recognizing Human-Object Interactions”, In CVPR, 2018.