Inter-X: Towards Versatile Human-Human Interaction Analysis
This dataset addresses limitations in existing resources for researchers in computer vision and social AI, though it is incremental as it builds on prior datasets by adding more data and annotations.
The authors tackled the problem of inaccurate body motions and lack of hand gestures in human-human interaction datasets by introducing Inter-X, a large dataset with ~11K sequences and 8.1M frames, featuring accurate movements and fine-grained annotations, which serves as a benchmark for versatile analysis tasks.
The analysis of the ubiquitous human-human interactions is pivotal for understanding humans as social beings. Existing human-human interaction datasets typically suffer from inaccurate body motions, lack of hand gestures and fine-grained textual descriptions. To better perceive and generate human-human interactions, we propose Inter-X, a currently largest human-human interaction dataset with accurate body movements and diverse interaction patterns, together with detailed hand gestures. The dataset includes ~11K interaction sequences and more than 8.1M frames. We also equip Inter-X with versatile annotations of more than 34K fine-grained human part-level textual descriptions, semantic interaction categories, interaction order, and the relationship and personality of the subjects. Based on the elaborate annotations, we propose a unified benchmark composed of 4 categories of downstream tasks from both the perceptual and generative directions. Extensive experiments and comprehensive analysis show that Inter-X serves as a testbed for promoting the development of versatile human-human interaction analysis. Our dataset and benchmark will be publicly available for research purposes.