{"ID":2922051,"CreatedAt":"2026-06-02T02:42:49.606572591Z","UpdatedAt":"2026-06-02T10:21:05.328072564Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.00662","arxiv_id":"2606.00662","title":"TAP-JEPA: Frozen Future-Latent Probing and Two-Stage Score Fusion for EPIC-KITCHENS-100 Action Anticipation","abstract":"This report presents TAP-JEPA, our runner-up submission to the EPIC-KITCHENS-100 (EK-100) Action Anticipation Challenge at EgoVis 2026. The task is to anticipate the next verb, noun, and verb-noun action from an egocentric clip that ends before the target action begins. Instead of fine-tuning a large video backbone, TAP-JEPA builds a compact anticipation model on frozen V-JEPA 2.1 features: a ViT-G/384 encoder extracts visible pre-action tokens, the pre-trained latent predictor estimates near-future tokens from the observed context, and both token groups are fused by attentive probes with task-specific queries for verbs, nouns, and action pairs. For the final submission, we expand supervised training with the official training split and most of the validation split, reserving a small subset for sanity checks and qualitative inspection, and adopt a two-stage score fusion that first averages eight independently initialized probe replicas within each epoch and then merges candidates from epochs 12-20 with field-dependent weights. On the official open-testing leaderboard, our sunshinesky entry achieves 27.91 percent overall action Mean Top-5 Recall (MT5R), ranking second and only 0.04 percentage points behind the top score.","short_abstract":"This report presents TAP-JEPA, our runner-up submission to the EPIC-KITCHENS-100 (EK-100) Action Anticipation Challenge at EgoVis 2026. The task is to anticipate the next verb, noun, and verb-noun action from an egocentric clip that ends before the target action begins. Instead of fine-tuning a large video backbone, TA...","url_abs":"https://arxiv.org/abs/2606.00662","url_pdf":"https://arxiv.org/pdf/2606.00662v1","authors":"[\"Chaoyang Wang\",\"Lexuan Xu\"]","published":"2026-05-30T10:23:12Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}