
A novel multi-scale memory matching and decoding scheme with clip-based time-coded memory, and a transformation-aware loss, to effectively track objects undergoing complex transformations, small objects, and in long videos.


coremsg

tam-vt-transformation-aware-multi-scale-video-transformer-for-segmentation-and-tracking


TAM-VT: Transformation-Aware Multi-scale Video Transformer for Segmentation and Tracking


title_rewrite


The proposed spatial-temporal multi-level association (STMA) framework efficiently learns dynamic, target-aware features by jointly associating reference frame, test frame, and object features, and utilizes a spatial-temporal memory bank to assist feature association and temporal ID assignment for accurate video object segmentation.


spatial-temporal-multi-level-association-for-efficient-and-accurate-video-object-segmentation


Spatial-Temporal Multi-level Association for Efficient and Accurate Video Object Segmentation



A novel end-to-end framework that leverages the unique properties of event cameras to enhance video object segmentation accuracy under low-light conditions.


event-assisted-video-object-segmentation-in-low-light-conditions


Event-Assisted Video Object Segmentation in Low-Light Conditions
