AI Paper Atlas

Research map / Detection and segmentation / Tracking

"SLAck: Semantic, Location, and Appearance Aware Open-Vocabulary Tracking"

Siyuan Li, Lei Ke, Yung-Hsu Yang, Luigi Piccinelli, Mattia Segù, Martin Danelljan, Luc Van Gool

ECCV 2024 · Detection and segmentation › Tracking · approach: Association cues for online MOT · 10 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add semantic cue to location-only association (ablation)Lck · TAO open-vocab val novelAssocA: 28.3 -> 35.4Improved
add semantic cue to appearance-only association (ablation)Ack · TAO open-vocab val novelAssocA: 32.7 -> 35.1Improved
add semantic cue to location+appearance tracker (ablation)LAck · TAO open-vocab val novelAssocA: 36.4 -> 37.8Improved
detection-aware training instead of training on sparse ground truth (ablation)SLAck · TAO open-vocab val novelAssocA: 24.1 -> 37.8Improved
hard class grouping of semantic cues instead of no semantics (ablation)TETer-T · TAO TETAAssocA: 35.2 -> 30.6Hurt
soft grouping with BERT embeddings (ablation)TETer-T · TAO TETAAssocA: 35.2 -> 31.2Hurt
early semantic-aware matching instead of CEM soft grouping (ablation)TETer-T · TAO TETAAssocA: 36.7 -> 38.0Improved
use semantic cue alone instead of appearance alone in STOG (ablation)STOG tracker · TAO open-vocab val novelAssocA: -4.4 AssocAHurt
add spatial and temporal object graph (STOG) to all three cues (ablation)SLAck · TAO open-vocab val novelAssocA: 34.1 -> 37.8Improved
add STOG to semantic-only tracker (ablation)Sck · TAO open-vocab val novelAssocA: 28.7 -> 28.4No clear effect
add dynamic score thresholding at inference (ablation)SLAck · TAO open-vocab val novelLocA: 50.5 -> 54.3Improved
use addition instead of concatenation for cue fusion (ablation)SLAck · TAO open-vocab val novelAssocA: 35.8 -> 37.8Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy