%0 Generic %1 citeulike:14643356 %A xxx, %D 2018 %K attention interaction loss %T iCAN: Instance-Centric Attention Network for Human-Object Interaction Detection %U http://arxiv.org/abs/1808.10437 %X 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 these cues, 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.

@misc{citeulike:14643356, 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 these cues, 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.}}, added-at = {2019-02-27T22:23:29.000+0100}, archiveprefix = {arXiv}, author = {xxx}, biburl = {https://www.bibsonomy.org/bibtex/23a6892450cb2c5da4793483847a08ff0/nmatsuk}, citeulike-article-id = {14643356}, citeulike-linkout-0 = {http://arxiv.org/abs/1808.10437}, citeulike-linkout-1 = {http://arxiv.org/pdf/1808.10437}, day = 30, eprint = {1808.10437}, interhash = {1bdd488b672485838763bd459bcd471d}, intrahash = {3a6892450cb2c5da4793483847a08ff0}, keywords = {attention interaction loss}, month = aug, posted-at = {2018-10-05 12:25:24}, priority = {2}, timestamp = {2019-02-27T22:23:29.000+0100}, title = {{iCAN: Instance-Centric Attention Network for Human-Object Interaction Detection}}, url = {http://arxiv.org/abs/1808.10437}, year = 2018 }