TrajTok learns to tokenize video into object-trajectory tokens end-to-end, improving video CLIP, probing, and VLM performance over patch and token-merging baselines.
Scal- ing slot attention for unsupervised object discovery
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
TrajTok: Learning Trajectory Tokens enables better Video Understanding
TrajTok learns to tokenize video into object-trajectory tokens end-to-end, improving video CLIP, probing, and VLM performance over patch and token-merging baselines.