Pith. sign in

Anticipative video transformer

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.CV 1

years

2025 1

verdicts

REJECT 1

roles

background 1

polarities

unclear 1

representative citing papers

Overcoming Semantic Dilution in Transformer-Based Next Frame Prediction

cs.CV · 2025-01-28 · reject · novelty 4.0

A transformer next-frame predictor that feeds each attention head the full embedding and trains on embedding-space loss reports gains on three video datasets, but the comparison is confounded by using the training objective as the test metric.

citing papers explorer

Showing 1 of 1 citing paper.

  • Overcoming Semantic Dilution in Transformer-Based Next Frame Prediction cs.CV · 2025-01-28 · reject · none · ref 6

    A transformer next-frame predictor that feeds each attention head the full embedding and trains on embedding-space loss reports gains on three video datasets, but the comparison is confounded by using the training objective as the test metric.