arXiv Computer Vision
MaST: Motion-aware Sparse Pipeline for Lightweight Object Tracking
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
Hugging Face Trending Papers
Aug 25
MaST: Motion-aware Sparse Pipeline for Lightweight Object Tracking
Transformer-based object trackers are renowned for their strong performance, yet dense token processing often leads to prohibitive computational cost, limiting real-time deployment on edge devices. Wh...
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.
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 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.
arXiv Computer Vision
5d ago
SV-TAD: Native Sparse Convs for Efficient Temporal Action Detection
SV-TAD introduces native sparse 2D convolutions to enable convolutional adapters to operate directly on dynamically pruned token sets, addressing the inefficiency of dense reconstruction in token‑selection methods. By integrating this primitive into a temporal action detection framework, the approach cuts VideoMAEv2‑L computation by up to 64% and achieves 2.2× faster inference while preserving state‑of‑the‑art accuracy on THUMOS‑14 and ActivityNet‑1.3. When applied to InternVideoNext‑L, it surpasses prior state‑of‑the‑art performance at roughly half the computational cost and naturally supports auxiliary task tokens for improved fine‑grained assembly detection on ATTACH.