📹 Video Understanding

🧠 NeurIPS2026 · 1 paper notes

📌 Same area in other venues: 🎞️ ECCV2026 (110) · 📷 CVPR2026 (187) · 🔬 ICLR2026 (48) · 🧪 ICML2026 (17) · 🤖 AAAI2026 (27) · 🧠 NeurIPS2025 (39)

TT-VidT: Decoupling the Temporal Axis for Efficient Motion-Centric Video Pretraining

TT-VidT reconstructs later frames using a first-frame anchor that retains full spatial information and compact learned motion tokens, substantially improving motion-sensitive tasks under a shared recipe of roughly 1.7 million videos and 8 epochs while reducing TT3D encoder compute to 456.1 GF, without establishing universal video-understanding superiority or strict appearance–motion disentanglement.