Pith. sign in

REVIEW 1 cited by

TAPTRv2: Attention-based Position Update Improves Tracking Any Point

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2407.16291 v2 pith:VPXDQPKL submitted 2024-07-23 cs.CV cs.RO

classification cs.CVcs.RO
keywords taptrv2pointquerycost-volumetaptrattentionoperationposition
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In this paper, we present TAPTRv2, a Transformer-based approach built upon TAPTR for solving the Tracking Any Point (TAP) task. TAPTR borrows designs from DEtection TRansformer (DETR) and formulates each tracking point as a point query, making it possible to leverage well-studied operations in DETR-like algorithms. TAPTRv2 improves TAPTR by addressing a critical issue regarding its reliance on cost-volume,which contaminates the point query\'s content feature and negatively impacts both visibility prediction and cost-volume computation. In TAPTRv2, we propose a novel attention-based position update (APU) operation and use key-aware deformable attention to realize. For each query, this operation uses key-aware attention weights to combine their corresponding deformable sampling positions to predict a new query position. This design is based on the observation that local attention is essentially the same as cost-volume, both of which are computed by dot-production between a query and its surrounding features. By introducing this new operation, TAPTRv2 not only removes the extra burden of cost-volume computation, but also leads to a substantial performance improvement. TAPTRv2 surpasses TAPTR and achieves state-of-the-art performance on many challenging datasets, demonstrating the superiority

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. ProTracker: Probabilistic Integration for Robust and Accurate Point Tracking

    cs.CV 2025-01 conditional novelty 5.0 of 10

    ProTracker merges optical flow predictions with long-term keypoint matches through probabilistic integration, achieving the highest point-position accuracy on TAP-Vid and BADJA.

Pith tools