Hugging Face Trending Papers
MaST: Motion-aware Sparse Pipeline for Lightweight Object Tracking
Read the original on Hugging Face Trending Papers →The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
Related stories
arXiv Computer Vision
Aug 26
MaST: Motion-aware Sparse Pipeline for Lightweight Object Tracking
arXiv:2608.24365v1 Announce Type: new Abstract: Transformer-based object trackers are renowned for their strong performance, yet dense token processing often leads to prohibitive computational cost,...
Hugging Face Trending Papers
Aug 11
MVTrack: Ultrafast Appearance-Free Moving Object Tracking from Compressed Bitstreams
Deploying modern video trackers at scale is bottlenecked by the computational cost of RGB-based object detectors. To this end, we present MVTrack, an ultrafast tracker for moving objects that operates directly on H.
arXiv AI
Aug 12
MVTrack: Ultrafast Appearance-Free Moving Object Tracking from Compressed Bitstreams
arXiv:2608. 10790v1 Announce Type: cross Abstract: Deploying modern video trackers at scale is bottlenecked by the computational cost of RGB-based object detectors.
arXiv Computer Vision
Aug 24
Tetris: Tile-level Sampling for Efficient and High-Fidelity Video Object Tracking
Tetris is a video object tracking system that uses tile-level sampling to efficiently extract high‑fidelity tracks. It partitions videos into tile‑based polyominoes, classifies relevant tiles, prunes redundant ones with an ILP under a user‑defined accuracy constraint, and packs the remaining polyominoes to minimize detector calls. On seven stationary‑video datasets, Tetris maintains less than a 5% loss in tracking accuracy while achieving up to 17.4× higher throughput than prior systems and up to 68.8× higher than a full‑frame reference pipeline.
arXiv AI
Sep 25
TrackEverything: Long Horizon Dense Tracking via De-Duplicating 3D Scene Representations
TrackEverything is a 3D point tracker that overcomes the trade‑off between sparse long‑horizon tracking and dense short‑clip tracking by representing videos as persistent 3D scene tracks in world coordinates. It introduces voxel‑based de‑duplication at sliding‑window boundaries, a two‑stage refinement process (endpoint refiner and lightweight trajectory refiner), and a 3D WAFT module that replaces memory‑heavy 4D correlation volumes with efficient feature sampling. The method can track all visible points in videos longer than 1000 frames using only 40 GB of GPU memory, outperforming existing dense trackers on short clips and matching sparse trackers on long sequences.
Hugging Face Trending Papers
Sep 29
ByteTraX: Enhancing the ByteTrack Architecture with Optimised Thresholding
The ByteTrack algorithm is a widely used and computationally efficient multi-object tracking architecture. Its core innovation lies in the combination of lenient bounding box associations with trackle...