The Overlooked Classifier in Human-Object Interaction Recognition
Human-Object Interaction (HOI) recognition is challenging due to two factors: (1) significant imbalance across classes and (2) requiring multiple labels per image. This paper shows that these two challenges can be effectively addressed by improving the classifier with the backbone architecture untouched. Firstly, we encode the semantic correlation among classes into the classification head by initializing the weights with language embeddings of HOIs. As a result, the performance is boosted significantly, especially for the few-shot subset. Secondly, we propose a new loss named LSE-Sign to enhance multi-label learning on a long-tailed dataset. Our simple yet effective method enables detection-free HOI classification, outperforming the state-of-the-arts that require object detection and human pose by a clear margin. Moreover, we transfer the classification model to instance-level HOI detection by connecting it with an off-the-shelf object detector. We achieve state-of-the-art without additional fine-tuning.
Code (0)
등록된 구현이 없습니다.
Tasks
ClassificationHuman-Object Interaction DetectionMulti-Label LearningObjectobject-detectionObject DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
The Overlooked Classifier in Human-Object Interaction Recognition
Human-Object Interaction (HOI) recognition is challenging due to two factors: (1) significant imbalance across classes and (2) requiring multiple labels per image. This paper shows that these two challenges can be effect…
ClassificationHuman-Object Interaction DetectionMulti-Label LearningObject+2Object Recognition with Human in the Loop Intelligent Frameworks
Classifiers embedded within human in the loop visual object recognition frameworks commonly utilise two sources of information: one derived directly from the imagery data of an object, and the other obtained interactivel…
ObjectObject RecognitionSimultaneous Detection and Interaction Reasoning for Object-Centric Action Recognition
The interactions between human and objects are important for recognizing object-centric actions. Existing methods usually adopt a two-stage pipeline, where object proposals are first detected using a pretrained detector,…
Action RecognitionFew-Shot action recognitionFew Shot Action RecognitionObject+2Multimodal Uncertainty Reduction for Intention Recognition in Human-Robot Interaction
Assistive robots can potentially improve the quality of life and personal independence of elderly people by supporting everyday life activities. To guarantee a safe and intuitive interaction between human and robot, huma…
Intent DetectionIs Object Detection Necessary for Human-Object Interaction Recognition?
This paper revisits human-object interaction (HOI) recognition at image level without using supervisions of object location and human pose. We name it detection-free HOI recognition, in contrast to the existing detection…
Human-Object Interaction DetectionObjectobject-detectionObject Detection