← Authors

Pichao WANG

28 papers · 2017–2026 · 8 conferences · across top CS/AI conferences

Achievements

🌈 Renaissance Researcher (6) 🐣 Hot Topic Early Bird πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (7) πŸƒ Academic Marathon (8) πŸ—ΊοΈ Taxonomy Completionist (55) 🐝 Cross-Pollinator (10) 🀝 Dynamic Duo (12) πŸ”¬ Deep Specialist (10) 🧬 Topic Evolution πŸ† Keyword Champion (2) πŸ”₯ Unstoppable (6) ⚑ Prolific Year (8) ❓ The Questioner πŸ’Ž Century Club (27) πŸ—ƒοΈ Keyword Collector (139)

Conferences

CVPR (9) ICCV (5) AAAI (4) NIPS (4) ECCV (2) ICLR (2) ACL (1) EACL (1)

Top co-authors

Fan Wang (12) Hao Li (9) Rong Jin (7) Hao Luo (5) Mike Zheng Shou (4) Ming Lin (3) Shuning Chang (3) Zhiqiang Tao (2) Majid Rabbani (2) Jiamian Wang (2)

Keywords

vision transformer (6) 3d vision (3) multimodal learning (3) human pose estimation (3) frequency domain (2) model efficiency (2) text-video retrieval (2) 3d human pose estimation (2) diffusion model (2) temporal modeling (2) image generation (2) transformer architecture (2) semantic segmentation (2) embedding space (2) model compression (2) cross-modal retrieval (2) token pruning (2) video understanding (2) efficient computing (2) rgb-d recognition (2)

Papers

Do Audio LLMs Really LISTEN, or Just Transcribe? Measuring Lexical vs. Acoustic Emotion Cues Reliance EACL 2026
CRPO: Confidence-Reward Driven Preference Optimization for Machine Translation ACL 2025
Bridging Information Asymmetry in Text-video Retrieval: A Data-centric Approach ICLR 2025
Training-Free Text-Guided Image Editing with Visual Autoregressive Model ICCV 2025
Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation CVPR 2024
One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos NIPS 2024
Diffusion-Inspired Truncated Sampler for Text-Video Retrieval NIPS 2024
Text Is MASS: Modeling as Stochastic Embedding for Text-Video Retrieval CVPR 2024
Enhancing Motion in Text-to-Video Generation with Decomposed Encoding and Conditioning NIPS 2024
Making Vision Transformers Efficient From a Token Sparsification View CVPR 2023
Head-Free Lightweight Semantic Segmentation with Linear Transformer AAAI 2023
Frequency Domain Disentanglement for Arbitrary Neural Style Transfer AAAI 2023
PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation CVPR 2023
Selective Structured State-Spaces for Long-Form Video Understanding CVPR 2023
Revisiting Vision Transformer from the View of Path Ensemble ICCV 2023
Audio-Enhanced Text-to-Video Retrieval using Text-Conditioned Feature Alignment ICCV 2023
CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation ICLR 2022
EPro-PnP: Generalized End-to-End Probabilistic Perspective-N-Points for Monocular Object Pose Estimation CVPR 2022
KVT: k-NN Attention for Boosting Vision Transformers ECCV 2022
TransFGU: A Top-down Approach to Fine-Grained Unsupervised Semantic Segmentation ECCV 2022
Scaled ReLU Matters for Training Vision Transformers AAAI 2022
Decoupling and Recoupling Spatiotemporal Representation for RGB-D-Based Motion Recognition CVPR 2022
VTC-LFC: Vision Transformer Compression with Low-Frequency Components NIPS 2022
MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation CVPR 2022
TransReID: Transformer-Based Object Re-Identification ICCV 2021
Zen-NAS: A Zero-Shot NAS for High-Performance Image Recognition ICCV 2021
RΒ²MRF: Defocus Blur Detection via Recurrently Refining Multi-Scale Residual Features AAAI 2020
Scene Flow to Action Map: A New Representation for RGB-D Based Action Recognition With Convolutional Neural Networks CVPR 2017