Cvpr2026 Flashcache

Adaptive Spatial-Temporal Window: Unlocking the Potential of Event Cameras in Heterogeneous Velocity Scenarios Zhipeng Sui, ...

MixerCSeg: An Efficient Mixer Architecture for Crack Segmentation via Decoupled Mamba Attention.

Disentangle-then-Align: Non-Iterative Hybrid Multimodal Image Registration via Cross-Scale Feature Disentanglement.

In this video, we introduce a novel video object detection framework called D2FANet. D2FANet is the first framework to jointly ...

[

Chengxing Lin, Jinhong Deng, Yinjie Lei, Wen Li. "Deformation-based In-Context Learning for Point Cloud Understanding.

[CVPR 2026]SFR-Net: Steering-Fusion-Refining Network in Multi-label Zero-Shot Sewer Defect Detection

Official video for the

PA-Attack: Guiding Gray-Box Attacks on LVLM Vision Encoders with Prototypes and Attention.

Video presentation of our

This video presents GHPT, a novel framework for real-time relightable Gaussian Splatting using hybrid path tracing. Project Page: ...

The 5-minute introduction video of IntrinsicWeather.

Towards Open-Vocabulary Industrial Defect Understanding with a Large-Scale Multimodal Dataset.

TAPE: Task-Adaptive Prototype Evolution in Audio-Language Models for Fully Few-shot Class-incremental Audio Classification.

This is the official 5-minute poster presentation video for

FlashDecoder: Real-Time Latent-to-Pixel Streaming Decoder with Transformers.

[CVPR 2026] Content-Adaptive Hierarchical Hyperprior for Neural Video Coding

This is an introduction video for our work submitted to

This is a talk about

[Project website]: https://woo525.github.io/DEBIR/ [Paper]: https://arxiv.org/abs/2603.21784 [Code]: ...