CVPR 2024 论文和代码速递！ 2024.4.16

整理：AI算法与图像处理

欢迎关注公众号 AI算法与图像处理，获取更多干货：

推荐

微信交流群现已有2000+从业人员交流群，欢迎进群交流学习，微信：nvshenj125

B站最新成果demo分享地址：https://space.bilibili.com/288489574

顶会工作整理Github repo：https://github.com/DWCTOD/CVPR2023-Papers-with-Code-Demo

工作整理

CVPR 2024

Updated on : 16 Apr 2024

total number : 22

No More Ambiguity in 360° Room Layout via Bi-Layout Estimation

• 论文/Paper: http://arxiv.org/pdf/2404.09993




• 代码/Code: None

One-Click Upgrade from 2D to 3D: Sandwiched RGB-D Video Compression for Stereoscopic Teleconferencing

• 论文/Paper: http://arxiv.org/pdf/2404.09979




• 代码/Code: None

Video2Game: Real-time, Interactive, Realistic and Browser-Compatible Environment from a Single Video

• 论文/Paper: http://arxiv.org/pdf/2404.09833




• 代码/Code: None

3D Face Tracking from 2D Video through Iterative Dense UV to Image Flow

• 论文/Paper: http://arxiv.org/pdf/2404.09819




• 代码/Code: None

FSRT: Facial Scene Representation Transformer for Face Reenactment from Factorized Appearance, Head-pose, and Facial Expression Features

• 论文/Paper: http://arxiv.org/pdf/2404.09736




• 代码/Code: None

The revenge of BiSeNet: Efficient Multi-Task Image Segmentation

• 论文/Paper: http://arxiv.org/pdf/2404.09570




• 代码/Code: None

Learning Tracking Representations from Single Point Annotations

• 论文/Paper: http://arxiv.org/pdf/2404.09504




• 代码/Code: None

SparseOcc: Rethinking Sparse Latent Representation for Vision-Based Semantic Occupancy Prediction

• 论文/Paper: http://arxiv.org/pdf/2404.09502




• 代码/Code: None

TCCT-Net: Two-Stream Network Architecture for Fast and Efficient Engagement Estimation via Behavioral Feature Signals

• 论文/Paper: http://arxiv.org/pdf/2404.09474




• 代码/Code: https://github.com/vedernikovphoto/tcct_net

PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AI

• 论文/Paper: http://arxiv.org/pdf/2404.09465




• 代码/Code: None

Contrastive Mean-Shift Learning for Generalized Category Discovery

• 论文/Paper: http://arxiv.org/pdf/2404.09451




• 代码/Code: None

The 8th AI City Challenge

• 论文/Paper: http://arxiv.org/pdf/2404.09432




• 代码/Code: None

DetCLIPv3: Towards Versatile Generative Open-vocabulary Object Detection

• 论文/Paper: http://arxiv.org/pdf/2404.09216




• 代码/Code: None

Coreset Selection for Object Detection

• 论文/Paper: http://arxiv.org/pdf/2404.09161




• 代码/Code: None

Exploring Explainability in Video Action Recognition

• 论文/Paper: http://arxiv.org/pdf/2404.09067




• 代码/Code: None

PracticalDG: Perturbation Distillation on Vision-Language Models for Hybrid Domain Generalization

• 论文/Paper: http://arxiv.org/pdf/2404.09011




• 代码/Code: None

MMA-DFER: MultiModal Adaptation of unimodal models for Dynamic Facial Expression Recognition in-the-wild

• 论文/Paper: http://arxiv.org/pdf/2404.09010




• 代码/Code: None

MCPNet: An Interpretable Classifier via Multi-Level Concept Prototypes

• 论文/Paper: http://arxiv.org/pdf/2404.08968




• 代码/Code: None

AMU-Tuning: Effective Logit Bias for CLIP-based Few-shot Learning

• 论文/Paper: http://arxiv.org/pdf/2404.08958




• 代码/Code: https://github.com/tju-sjyj/amu-tuning

Label-free Anomaly Detection in Aerial Agricultural Images with Masked Image Modeling

• 论文/Paper: http://arxiv.org/pdf/2404.08931




• 代码/Code: None

`Eyes of a Hawk and Ears of a Fox': Part Prototype Network for Generalized Zero-Shot Learning

• 论文/Paper: http://arxiv.org/pdf/2404.08761




• 代码/Code: None

Exploring Text-to-Motion Generation with Human Preference

• 论文/Paper: http://arxiv.org/pdf/2404.09445




• 代码/Code: None