Motion Guided Attention Fusion to Recognize Interactions from Videos
This work addresses the problem of recognizing detailed interactions in videos for applications like action recognition, showing incremental improvements over prior dual-stream methods.
The paper tackles fine-grained interaction recognition in videos by introducing a dual-pathway approach with separate motion and object detection pathways, enhanced by a Motion-Guided Attention Fusion module. It outperforms state-of-the-art methods on the Something-Something-v2 dataset and generalizes well to real-world tasks like IKEA furniture assembly.
We present a dual-pathway approach for recognizing fine-grained interactions from videos. We build on the success of prior dual-stream approaches, but make a distinction between the static and dynamic representations of objects and their interactions explicit by introducing separate motion and object detection pathways. Then, using our new Motion-Guided Attention Fusion module, we fuse the bottom-up features in the motion pathway with features captured from object detections to learn the temporal aspects of an action. We show that our approach can generalize across appearance effectively and recognize actions where an actor interacts with previously unseen objects. We validate our approach using the compositional action recognition task from the Something-Something-v2 dataset where we outperform existing state-of-the-art methods. We also show that our method can generalize well to real world tasks by showing state-of-the-art performance on recognizing humans assembling various IKEA furniture on the IKEA-ASM dataset.