arXiv:2608. 10790v1 Announce Type: cross Abstract: Deploying modern video trackers at scale is bottlenecked by the computational cost of RGB-based object detectors.
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: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,...
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...
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:2606. 14094v1 Announce Type: cross Abstract: Conventional RGB cameras have been widely used in multi-object tracking due to their ability to capture rich appearance and semantic information.
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.
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.
ByteTraX is a lightweight enhancement to the ByteTrack multi‑object tracking architecture that introduces a single unified matching threshold and stricter track initiation criteria to reduce erroneous track reclassification and identity switches. The method yields consistent performance gains across several benchmarks—GMOT‑40, LC‑MOT, SportsMOT, TeamTrack, DAMUNT, and DeepSea‑MOT—while boosting processing speed by over 10%. Quantitatively, ByteTraX achieves more than a 40% drop in identity switches, with mean improvements of 3.6 in HOTA, 5.6 in IDF1, and 6.3 FPS.
PointEvent introduces serialized motion evidence accumulation for event-based tiny object detection, treating motion continuity as an ordered evidence propagation process. The method organizes event streams into locality‑preserving spatiotemporal paths and chronology‑preserving temporal paths, alternating serialized scans across complementary orders to consolidate fragmented motion evidence. A lightweight event‑wise state‑space framework with a high‑resolution event branch and compact context modulation achieves state‑of‑the‑art performance with the fewest parameters and fastest inference among compared methods.
arXiv:2501.15119v3 Announce Type: replace Abstract: Existing computer vision pipelines suffer from two efficiency bottlenecks: image signal processors (ISPs) first convert Bayer pixel data to RGB pix...
To adapt billion-parameter Vision Transformers for long-video understanding, recent methods freeze the backbone and train lightweight convolutional modules. While effective for parameter-efficient tra...
arXiv:2607. 14898v1 Announce Type: cross Abstract: Real-time video generation demands fast decoding as much as fast denoising, yet current latent video diffusion models rely on 3D convolutional decoders that are slow and memory-intensive at high resolutions or for long video.