ACTrack: Adding Spatio-Temporal Condition for Visual Object Tracking
Efficiently modeling spatio-temporal relations of objects is a key challenge in visual object tracking (VOT). Existing methods track by appearance-based similarity or long-term relation modeling, resulting in rich temporal contexts between consecutive frames being easily overlooked. Moreover, training trackers from scratch or fine-tuning large pre-trained models needs more time and memory consumption. In this paper, we present ACTrack, a new tracking framework with additive spatio-temporal conditions. It preserves the quality and capabilities of the pre-trained Transformer backbone by freezing its parameters, and makes a trainable lightweight additive net to model spatio-temporal relations in tracking. We design an additive siamese convolutional network to ensure the integrity of spatial features and perform temporal sequence modeling to simplify the tracking pipeline. Experimental results on several benchmarks prove that ACTrack could balance training efficiency and tracking performance.
Code (0)
등록된 구현이 없습니다.
Tasks
ObjectObject TrackingVisual Object TrackingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
BACTrack: Building Appearance Collection for Aerial Tracking
Siamese network-based trackers have shown remarkable success in aerial tracking. Most previous works, however, usually perform template matching only between the initial template and the search region and thus fail to de…
GPUTemplate MatchingA Survey on Spatio-temporal Data Analytics Systems
Due to the surge of spatio-temporal data volume, the popularity of location-based services and applications, and the importance of extracted knowledge from spatio-temporal data to solve a wide range of real-world problem…
SurveyAdapEdit: Spatio-Temporal Guided Adaptive Editing Algorithm for Text-Based Continuity-Sensitive Image Editing
With the great success of text-conditioned diffusion models in creative text-to-image generation, various text-driven image editing approaches have attracted the attentions of many researchers. However, previous works ma…
Image GenerationText to Image GenerationText-to-Image GenerationModels as Tools: An Agentic Coordination Framework for Unified Multimodal Visual Tracking
Most current visual trackers adopt a matching-based architecture trained exclusively on tracking datasets, whose performance gains depend heavily on the length of the input context, and have now reached a bottleneck. Whi…
Visual TrackingTubeRMC: Tube-conditioned Reconstruction with Mutual Constraints for Weakly-supervised Spatio-Temporal Video Grounding
Spatio-Temporal Video Grounding (STVG) aims to localize a spatio-temporal tube that corresponds to a given language query in an untrimmed video. This is a challenging task since it involves complex vision-language unders…
Spatio-Temporal Video GroundingVisual Grounding