Enhancing Self-Supervised Fine-Grained Video Object Tracking with Dynamic Memory Prediction
This work addresses the challenge of accurate pixel recognition in videos for applications like surveillance or autonomous driving, representing an incremental improvement over existing self-supervised methods.
The paper tackles the problem of fine-grained video object tracking by introducing a Dynamic Memory Prediction framework that uses multiple reference frames to enhance frame reconstruction, achieving state-of-the-art performance in self-supervised object segmentation and keypoint tracking tasks.
Successful video analysis relies on accurate recognition of pixels across frames, and frame reconstruction methods based on video correspondence learning are popular due to their efficiency. Existing frame reconstruction methods, while efficient, neglect the value of direct involvement of multiple reference frames for reconstruction and decision-making aspects, especially in complex situations such as occlusion or fast movement. In this paper, we introduce a Dynamic Memory Prediction (DMP) framework that innovatively utilizes multiple reference frames to concisely and directly enhance frame reconstruction. Its core component is a Reference Frame Memory Engine that dynamically selects frames based on object pixel features to improve tracking accuracy. In addition, a Bidirectional Target Prediction Network is built to utilize multiple reference frames to improve the robustness of the model. Through experiments, our algorithm outperforms the state-of-the-art self-supervised techniques on two fine-grained video object tracking tasks: object segmentation and keypoint tracking.