arXiv Computer Vision
ByteAction: Byte-space Action Recognition Foundation Model
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Aug 25
Towards Bitstream-corrupted Harsh Visual Understanding: Through Bitstream Language Modeling as Robust Semantic Priors
arXiv:2608.21837v1 Announce Type: new Abstract: Bitstream-corrupted Harsh Visual Understanding (BcHVU) aims to understand harshly degraded videos originally decoded from a severely corrupted bitstrea...
arXiv Computer Vision
1d ago
Image Bitstream Fine-grained Understanding for Privacy-Friendly AIoT
arXiv:2610.08414v1 Announce Type: new Abstract: Image Bitstream Fine-grained Understanding (IBFU) aims to directly perform fine-grained classification and semantic description generation from encoded...
arXiv Computer Vision
Sep 1
Asymmetric Phase Coding Video Watermarking
arXiv:2608.29212v1 Announce Type: cross Abstract: Existing video watermarking systems are symmetric: the party that can verify a mark holds the extractor weights or generator secret and can therefore...
arXiv Computer Vision
Oct 1
Semantic Watermarking for Malicious Image Manipulation Detection
arXiv:2609.39623v1 Announce Type: new Abstract: The proliferation of high-fidelity generative editing models has made it possible to inject violent or sexual content into otherwise ordinary images wh...
arXiv Computer Vision
Sep 23
COVER: Codec-Robust Video Watermarking with Generative Video Priors
COVER is a new video watermarking method that targets codec compression as its primary design goal. It embeds the watermark payload in the latent space of a frozen generative video autoencoder and recovers it by re‑encoding the received video into the same latent space. Using a differentiable codec surrogate bank, COVER achieves high bit accuracy across multiple codecs while keeping marked videos visually close to the originals.
arXiv AI
Jul 14
On Occlusions in Video Action Detection: Benchmark Datasets And Training Recipes
arXiv:2410. 19553v2 Announce Type: replace-cross Abstract: This paper explores the impact of occlusions in video action detection.