ICCV 2023

ICCV 2023 Link

Papers

ICCV 2023이 열리고 있다. NeRF, Multimodal/VQA, Model Compression 위주로 트래킹한다.
(일부 특이한 연구도 포함)

Neural Radiance Fields

  1. NeRF-MS: Neural Radiance Fields with Multi-Sequence
    Peihao Li et al.

  2. Re-ReND: Real-time Rendering of NeRFs across Devices
    Sara Rojas et al.

  3. CLNeRF: Continual Learning Meets NeRF
    Zhipeng Cai, Matthias Muller

  4. Single-Stage Diffusion NeRF: A Unified Approach to 3D Generation and Reconstruction
    Hansheng Chen et al.

  5. SceneRF: Self-Supervised Monocular 3D Scene Reconstruction with Radiance Fields
    Anh-Quan Cao, Raoul de Charette

  6. NerfAcc: Efficient Sampling Accelerates NeRFs
    Ruilong Li et al.

  7. FeatureNeRF: Learning Generalizable NeRFs by Distilling Foundation Models
    Jianglong Ye, Naiyan Wang, Xiaolong Wang

  8. ScatterNeRF: Seeing Through Fog with Physically-Based Inverse Neural Rendering
    Andrea Ramazzina et al.

  9. MonoNeRF: Learning a Generalizable Dynamic Radiance Field from Monocular Videos
    Fengrui Tian, Shaoyi Du, Yueqi Duan

Multimodal && VQA

  1. DIME-FM : DIstilling Multimodal and Efficient Foundation Models
    Ximeng Sun et al.

  2. VQA-GNN: Reasoning with Multimodal Knowledge via Graph Neural Networks for Visual Question Answering
    Yanan Wang et al.

  3. Localizing Moments in Long Video Via Multimodal Guidance
    Wayner Barrios et al.

  4. Decouple Before Interact: Multi-Modal Prompt Learning for Continual Visual Question Answering
    Zi Qian et al.

  5. Discovering Spatio-Temporal Rationales for Video Question Answering
    Yicong Li et al.

  6. Open-Vocabulary Video Question Answering: A New Benchmark for Evaluating the Generalizability of Video Question Answering Models
    Dogwab Ko et al.

  7. Variational Causal Inference Network for Explanatory Visual Question Answering
    Dizhan Xue et al.

  8. Toward Unsupervised Realistic Visual Question Answering
    Yuwei Zhang et al.

  9. VQA-GNN: Reasoning with Multimodal Knowledge via Graph Neural Networks for Visual Question Answering
    Yanan Wang et al.

Quantization

  1. Jumping through Local Minima: Quantization in the Loss Landscape of Vision Transformers
    Natalia Frumkin, Dibakar Gope, Diana Marculescu

  2. EMQ: Evolving Training-free Proxies for Automated Mixed Precision Quantization
    Peijie Dong et al.

  3. DenseShift: Towards Accurate and Efficient Low-Bit Power-of-Two Quantization
    Xinlin Li et al.

  4. ResQ: Residual Quantization for Video Perception
    Davide Abati et al.

  5. I-ViT: Integer-only Quantization for Efficient Vision Transformer Inference
    Zhikai Li, Qingyi Gu

  6. RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformers
    Zhikai Li et al.

  7. Unified Data-Free Compression: Pruning and Quantization without Fine-TuningTeachers
    Shipeng Bai et al.

  8. A2Q: Accumulator-Aware Quantization with Guaranteed Overflow Avoidance
    Ian Colbert et al.

Distillation

  1. TinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritance
    Kan Wu et al.

  2. DOT: A Distillation-Oriented Trainer
    Borui Zhao et al.

  3. From Knowledge Distillation to Self-Knowledge Distillation: A Unified Approach with Normalized Loss and Customized Soft Labels
    Zhendong Yang et al.

  4. Cumulative Spatial Knowledge Distillation for Vision Transformers
    Borui Zhao et al.

  5. Multi-Label Knowledge Distillation
    Penghui Yang et al.

Etc

  1. Dataset Quantization
    Daquan Zhou, Kai Wang, Jianyang Gu, Xiangyu Peng, Dongze Lian, Yifan Zhang, Yang You, Jiashi Feng

  2. DREAM: Efficient Dataset Distillation by Representative Matching
    Yanqing Liu, Jianyang Gu, Kai Wang, Zheng Zhu, Wei Jiang, Yang You

  3. DataDAM: Efficient Dataset Distillation with Attention Matching
    Ahmad Sajedi et al.