arXiv Computer Vision

Image Classifiers are Efficient Self-Supervised Video Representation Learners

arXiv AI
Aug 28

LeVJEPA: Efficient & Scalable Video Pretraining without the Heuristics

LeVJEPA is a video encoder that eliminates the need for architectural asymmetries, exponential-moving-average target encoders, stop-gradients, and capacity-limited predictors used in prior self‑supervised methods. It trains a single encoder with an invariance loss over global and local views, regularized by SIGReg to prevent collapse, and achieves strong performance with far less pretraining compute. The approach also allows block‑causal attention, making temporal ordering a property of the encoder itself, and matches or surpasses state‑of‑the‑art baselines on both appearance‑centric and motion‑centric benchmarks.

By Lukas Kuhn, Lucas Maes, Giuseppe Serra, Quentin Le Lidec, Yann LeCun, Randall Balestriero, Florian Buettner
arXiv Computer Vision
Sep 7

Object Concepts Emerge from Motion

The paper introduces a biologically inspired framework that learns object‑centric visual representations from raw videos without human annotations or camera calibration. By using motion boundaries detected via optical flow and clustering to create pseudo‑instance masks, the method supervises a single‑image encoder with pixel‑level pairwise metric learning. Training on 195 million pseudo‑labeled frames and expanding to 421 million frames through Motion‑Verified Self‑Training, the approach yields Swin‑based encoders that outperform or match supervised and self‑supervised baselines on tasks such as monocular depth estimation, 3D object detection, 3D occupancy prediction, and end‑to‑end planning.

By Boshi Li, Xiaohui Wang, Xiaoyang Wu, Zhichao Li, Ya Yang, Naiyan Wang
arXiv Computer Vision
Oct 19

Dual-State Slot Attention: Decoupling Appearance and Identity for Video Object-Centric Learning

Dual-State Slot Attention (DSSA) is a self‑supervised framework that separates per‑frame appearance from temporally stable identity within each slot, addressing conflicts that cause slot swapping in video object‑centric learning. It introduces a learned recurrent transition for identity updates and competition‑modulated aggregation to suppress weakly matching slots, thereby improving segmentation quality and temporal consistency. Experiments on MOVi‑C, MOVi‑D, and YouTube‑VIS show DSSA outperforms prior methods and enhances downstream object recognition and video dynamics prediction.

By Sieu Tran, Duc Nguyen, Hao Vo, Khoa Vo, Ngan Le
Hugging Face Trending Papers
Aug 13

V-RAE: Rethinking Video Latent Spaces for Generation

Latent video generation relies on autoencoders to define a compact space in which generative models operate. Although video autoencoder architectures have evolved substantially, their latent spaces are still optimized primarily for pixel-level reconstruction and provide limited high-level semantic organization.

arXiv Computer Vision
Oct 23

Learning from Next-Frame Prediction: Towards Unified and Scalable Visual Representation Learning

The paper introduces VANE, a self‑supervised visual pretraining framework that learns from next‑frame prediction in embedding space. It uses a causal encoder to summarize past observations, a state predictor to infer the representation of the entire next frame, and a lightweight generative decoder to reconstruct fine‑grained spatial detail. By applying the same objective to both videos and still images through a local‑to‑global crop sequence, VANE achieves state‑of‑the‑art performance on anticipation, recognition, and dense perception benchmarks, notably outperforming V‑JEPA on EPIC‑KITCHENS‑100 action anticipation.

By Yifeng Yao, Jinghan Li, Zhihao Zhang, Yajiao Xiong, Yang Jin, Kun Xu, Huishuai Zhang, Dongyan Zhao
arXiv Computer Vision
Sep 30

TT-VidT: Decoupling the Temporal Axis for Efficient Motion-Centric Video Pretraining

TT-VidT is a video pretraining method that decouples the temporal axis by combining a per‑frame ViT-B/16 spatial encoder with a compact Temporal Transfer Layer trained via Diff Compression. The authors conduct a systematic 24‑configuration study to isolate architecture, objective, and decoder effects, showing that the full TT-VidT design yields the strongest motion‑sensitive representations. In downstream fine‑tuning, TT‑VidT outperforms state‑of‑the‑art baselines on Jester, Something‑Something V2, ARID, and Diving48 while using significantly fewer encoder FLOPs.

By Shih-Ying Yeh, Daniel Z. Kaplan, Xuehai Wang, Fu-En Yang, Min-Hung Chen, Shang-Hong Lai
arXiv Computer Vision
6d ago

Rethinking Evaluation for Video Capsule Endoscopy: Validation Protocol, Source-Video Diversity, and Cross-Dataset Shift

The paper introduces DMSNet, a deformable adaptive multi‑scale edge‑guided attention network for video capsule endoscopy (VCE) classification. It evaluates DMSNet and 18 other architectures on the Kvasir‑Capsule dataset using both random frame‑level and source‑video‑disjoint validation protocols, reporting MCC scores of 0.442 and 0.456 respectively. The study also examines cross‑dataset performance on CV2024, the impact of source‑video diversity, and shows that model rankings and accuracy vary significantly with validation protocol, training source diversity, and external dataset shift.

By Smriti Regmi, Debesh Jha