Skip to content
conftrace_

Xiyang Dai

38 papers · 2017–2026 · 8 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓
+11 more ↓ πŸ—ΊοΈ Taxonomy Completionist (63) 🌍 Conference Polyglot Β· Silver πŸƒ Academic Marathon Β· Sprint πŸŒ‰ Interdisciplinary Bridge Β· Gold 🐣 Hot Topic Early Bird
πŸ”¬ Deep Specialist (12) πŸ† Grand Slam 🀝 Dynamic Duo (29) 🌟 Keyword Trendsetter Combo (3) 🧭 Keyword Pioneer ⚑ Prolific Year Β· Productive πŸ“ˆ Trend Setter ❓ The Questioner πŸ”₯ Unstoppable Β· Bronze πŸ’Ž Century Club Β· Bronze πŸ—ƒοΈ Keyword Collector (186)

Venues

CVPR (15) NeurIPS (7) ICCV (5) ICLR (4) ECCV (3) EMNLP (2) AAAI (1) ICML (1)

Top co-authors

Lu Yuan (29) Dongdong Chen (19) Yinpeng Chen (18) Mengchen Liu (17) Jianwei Yang (12) Zicheng Liu (9) Jianfeng Gao (8) Pengchuan Zhang (7) Bin Xiao (7) Yu-Gang Jiang (7)

Research topics

Deep Learning (26) Computer Vision (23) Machine Learning (17) Analysis (17) Architectures (16) Learning Types Β· Deep Learning (11) Artificial Intelligence (10) Learning Types Β· Machine Learning (10) Techniques (10) Core AI Β· Artificial Intelligence (9) Processing (9) Application Areas (7) Core Methods (7) Natural Language Processing (5) Core AI Β· Computer Vision (5)

Keywords

object detection (10) vision transformer (7) convolutional neural network (6) image classification (5) semantic segmentation (5) zero-shot learning (4) contrastive learning (4) self-supervised learning (4) attention mechanism (4) video understanding (3) multimodal learning (3) efficient computing (3) self-attention mechanism (2) model architecture (2) few-shot learning (2) vision-language alignment (2) weakly supervised learning (2) visual question answering (2) representation learning (2) transfer learning (2)

Papers

LLM2CLIP: Powerful Language Model Unlocks Richer Cross-Modality Representation AAAI 2026 Exploring Invariance in Images through One-way Wave Equations ICML 2025 ProLongVid: A Simple but Strong Baseline for Long-context Video Instruction Tuning EMNLP 2025 DeepStack: Deeply Stacking Visual Tokens is Surprisingly Simple and Effective for LMMs NeurIPS 2024 Efficient Modulation for Vision Networks ICLR 2024 Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks CVPR 2024 Rewrite the Stars CVPR 2024 Detection Hub: Unifying Object Detection Datasets via Query Adaptation on Language Embedding CVPR 2023 Generalized Decoding for Pixel, Image, and Language CVPR 2023 LACMA: Language-Aligning Contrastive Learning with Meta-Actions for Embodied Instruction Following EMNLP 2023 Layer Grafted Pre-training: Bridging Contrastive Learning And Masked Image Modeling For Label-Efficient Representations ICLR 2023 Learning from Rich Semantics and Coarse Locations for Long-tailed Object Detection NeurIPS 2023 Look Before You Match: Instance Understanding Matters in Video Object Segmentation CVPR 2023 Masked Video Distillation: Rethinking Masked Feature Modeling for Self-Supervised Video Representation Learning CVPR 2023 BEVT: BERT Pretraining of Video Transformers CVPR 2022 Efficient Self-supervised Vision Transformers for Representation Learning ICLR 2022 Focal Modulation Networks NeurIPS 2022 GLIPv2: Unifying Localization and Vision-Language Understanding NeurIPS 2022 Mobile-Former: Bridging MobileNet and Transformer CVPR 2022 Reduce Information Loss in Transformers for Pluralistic Image Inpainting CVPR 2022 RegionCLIP: Region-Based Language-Image Pretraining CVPR 2022 Should All Proposals Be Treated Equally in Object Detection? ECCV 2022 Visual Clues: Bridging Vision and Language Foundations for Image Paragraph Captioning NeurIPS 2022 CvT: Introducing Convolutions to Vision Transformers ICCV 2021 Dynamic DETR: End-to-End Object Detection With Dynamic Attention ICCV 2021 Dynamic Head: Unifying Object Detection Heads With Attentions CVPR 2021 Focal Attention for Long-Range Interactions in Vision Transformers NeurIPS 2021 MicroNet: Improving Image Recognition With Extremely Low FLOPs ICCV 2021 Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding ICCV 2021 Revisiting Dynamic Convolution via Matrix Decomposition ICLR 2021 Stronger NAS with Weaker Predictors NeurIPS 2021 DA-NAS: Data Adapted Pruning for Efficient Neural Architecture Search ECCV 2020 Dynamic Convolution: Attention Over Convolution Kernels CVPR 2020 Dynamic ReLU ECCV 2020 METAL: Minimum Effort Temporal Activity Localization in Untrimmed Videos CVPR 2020 MAN: Moment Alignment Network for Natural Language Moment Retrieval via Iterative Graph Adjustment CVPR 2019 FASON: First and Second Order Information Fusion Network for Texture Recognition CVPR 2017 Temporal Context Network for Activity Localization in Videos ICCV 2017