2025春季学期组会
| 周次 | 时间地点 | 主讲人 | 主题 | 论文链接 | 备注 |
|---|---|---|---|---|---|
| 第$2$周 | 2月28日13:00 科技楼A座637 | 董大腾 | MixDehazeNet Mix Structure Block For Image Dehazing Network | MixDehazeNet Mix Structure Block For Image Dehazing Network | |
| 陈旭 | SAM-guided multi-level collaborative Transformer for infrared and visible image fusion | SAM-guided multi-level collaborative Transformer for infrared and visible image fusion | |||
| 第$3$周 | 3月7日13:00 科技楼A座637 | 王辉 | |||
| 苏世辉 | DRNet: Learning a dynamic recursion network for chaotic rain streak removal | DRNet: Learning a dynamic recursion network for chaotic rain streak removal | |||
| 第$4$周 | 3月14日13:00 科技楼A座637 | 陈卓扬 | Gandalf: Learning Label-Label Correlations in Extreme Multi-label Classification via Label Features | Gandalf: Learning Label-Label Correlations in Extreme Multi-label Classification via Label Features | |
| 第$5$周 | 3月20日13:00 科技楼A座637 | 陈逸霖 | Image Deraining with Frequency-Enhanced State Space Model | Image Deraining with Frequency-Enhanced State Space Model | |
| 第$6$周 | 3月28日13:00 科技楼A座637 | 荣泽语 | An Introduction to Prototype Contrastive Learning | ||
| 钟毅迪 | Colorful Diffuse Intrinsic Image Decomposition in the Wild | Colorful Diffuse Intrinsic Image Decomposition in the Wild | |||
| 第$8$周 | 4月11日13:00 科技楼A座637 | 张东辰 | Multi-stream feature aggregation network with multi-scale supervision for single image dehazing | Multi-stream feature aggregation network with multi-scale supervision for single image dehazing | |
| 第$9$周 | 4月18日13:00 科技楼A座637 | 董大腾 | CycFormer: Unsupervised Rain Removal Network Based on CycleGAN and Transformer | CycFormer: Unsupervised Rain Removal Network Based on CycleGAN and Transformer | |
| 陈旭 | AMLCA: Additive multi-layer convolution-guided cross-attention network for visible and infrared image fusion | AMLCA: Additive multi-layer convolution-guided cross-attention network for visible and infrared image fusion | |||
| 第$10$周 | 4月25日13:00 科技楼A座637 | 王辉 | Agent4Edu: Generating Learner Response Data by Generative Agents for Intelligent Education Systems | Agent4Edu: Generating Learner Response Data by Generative Agents for Intelligent Education Systems | |
| 钟毅迪 | |||||
| 第$12$周 | 5月9日13:00 科技楼A座637 | 陈卓扬 | PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentation | PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentation | |
| 孙逸晨 | Teacher Attention Measurement Based on Head Pose Estimation | Teacher Attention Measurement Based on Head Pose Estimation | Slides Used By 孙逸晨 | ||
| 第$13$周 | 5月16日13:00 科技楼A座637 | 陈逸霖 | MambaVision: A Hybrid Mamba-Transformer Vision Backbone | MambaVision: A Hybrid Mamba-Transformer Vision Backbone | |
| 第$14$周 | 5月23日13:00 科技楼A座637 | 苏世辉 | Parameter-efficient fine-tuning for single image snow removal | Parameter-efficient fine-tuning for single image snow removal | |
| 荣泽语 | Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs | Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs | |||
| 第$15$周 | 5月30日13:00 科技楼A座637 | 张东辰 | Real Scene Single Image Dehazing Network with Multi-Prior Guidance and Domain Transfer | Real Scene Single Image Dehazing Network with Multi-Prior Guidance and Domain Transfer | |
| 第$16$周 | 6月6日13:00 科技楼A座637 | 洪毅 | Hierarchical NeuroSymbolic Approach for Comprehensive and Explainable Action Quality Assessment | Hierarchical NeuroSymbolic Approach for Comprehensive and Explainable Action Quality Assessment | |
| 第$17$周 | 6月13日13:00 科技楼A座637 | 董大腾 | Dual-Pixel Raindrop Removal | Dual-Pixel Raindrop Removal | |
| 陈旭 | A full-scale hierarchical encoder-decoder network with cascading edge-prior for infrared and visible image fusion | A full-scale hierarchical encoder-decoder network with cascading edge-prior for infrared and visible image fusion | |||
| 第$18$周 | 6月20日13:00 科技楼A座637 | 钟毅迪 | IntrinsicNeRF: Learning Intrinsic Neural Radiance Fields for Editable Novel View Synthesis | IntrinsicNeRF: Learning Intrinsic Neural Radiance Fields for Editable Novel View Synthesis | |
| 第$19$周 | 6月27日13:00 科技楼A座637 | 王辉 | Training Turn-by-Turn Verifiers for Dialogue Tutoring Agents:The Curious Case of LLMs as Your Coding Tutors | Training Turn-by-Turn Verifiers for Dialogue Tutoring Agents:The Curious Case of LLMs as Your Coding Tutors | |
| 陈卓扬 | ADefMamba: Deformable Visual State Space Model | DefMamba: Deformable Visual State Space Model | |||
| 第$20$周 | 7月4日13:00 科技楼A座719 | 陈逸霖 | ACL: Activating Capability of Linear Attention for Image Restoration | ACL: Activating Capability of Linear Attention for Image Restoration | |
| 苏世辉 | Optimized connections and feature interactions for more efficient single-image desnowing | Optimized connections and feature interactions for more efficient single-image desnowing | |||