CVPR2024 | BestHub

AntTech

Jun 18, 2024 · Artificial Intelligence

Ant Group’s 24 Papers Featured at CVPR2024: Topics and Abstracts

The IEEE CVPR2024 conference in Seattle accepted 2,719 papers out of 11,532 submissions, and Ant Group contributed 24 papers covering computer vision, deep learning, digital humans, large models, multimodal remote sensing, vision‑language distillation, federated incremental learning, model‑stealing defense, and more, with one highlighted as a highlight.

Ant GroupCVPR2024Deep Learning

0 likes · 17 min read

Ant Group’s 24 Papers Featured at CVPR2024: Topics and Abstracts

Xiaohongshu Tech REDtech

May 10, 2024 · Artificial Intelligence

SIF3D: Sense‑Informed Forecasting of 3D Human Motion with Multimodal Attention

SIF3D is a scene‑aware 3D human motion forecasting framework that fuses observed motion, 3D point‑cloud scenes, and gaze through novel ternary intention‑aware and semantic‑coherence‑aware attention mechanisms, encoding with PointNet++ and Transformers, and decoding with a graph‑convolutional network, achieving state‑of‑the‑art results on GIMO and GTA‑1M benchmarks.

3D scene understandingCVPR2024SIF3D

0 likes · 15 min read

SIF3D: Sense‑Informed Forecasting of 3D Human Motion with Multimodal Attention

AntTech

Apr 24, 2024 · Artificial Intelligence

Snapshot Spectral Face Anti‑Spoofing Detection Framework Based on Supervised Contrastive Learning Wins CVPR2024 Challenge

The Ant Group Security Lab team achieved a perfect 0% error rate and first place in the snapshot spectral face anti‑spoofing track of the CVPR2024 Global Face Anti‑Spoofing Detection Challenge, showcasing a novel supervised contrastive learning framework that addresses data imbalance and improves detection of sophisticated spoof attacks.

CVPR2024computer visionface anti-spoofing

0 likes · 6 min read

Snapshot Spectral Face Anti‑Spoofing Detection Framework Based on Supervised Contrastive Learning Wins CVPR2024 Challenge