THUMOS-14

THUMOS-14 is a benchmark dataset that contains untrimmed videos annotated with action boundaries and categories, used to evaluate Temporal Action Localization (TAL) models.

Papers using THUMOS-14 (7)

DiGIT: Multi-Dilated Gated Encoder and Central-Adjacent Region Integrated Decoder for Temporal Action Detection Transformer2025 · 3 citesOZ-TAL: Online Zero-Shot Temporal Action Localization2026Hierarchical Multi-Stage Transformer Architecture for Context-Aware Temporal Action Localization2025Context-Enhanced Memory-Refined Transformer for Online Action Detection2025AFO-TAD: Anchor-free One-Stage Detector for Temporal Action Detection2019 · 3 citesA Multi-Modal Transformer Network for Action Detection2023Temporally smooth online action detection using cycle-consistent future anticipation2021