Computer Vision - Weekly Roundup

City-scale UAV navigation with satellite imagery reveals current VLN agents forget 40% of context after 379m, necessitating new memory architectures.

City-scale UAV navigation with satellite imagery reveals current VLN agents forget 40% of context after 379m, necessitating new memory architectures.

Recurrent token mixing via GTR achieves 58.9 AP on COCO with sub-2ms latency, offering a practical, efficient alternative to quadratic self-attention for high-resolution dense prediction.

This work builds Video-HopChain, a dataset of 22,550 multi-hop video questions over 13,378 videos, together with a held-out benchmark of 1,000 questions, which raises the mean over eight video understanding and reasoning benchmarks from 55.4 to 57.9 and introduces Confidence-Gated Exploration (CGE).

The Hierarchical Feature Integration Network is introduced, which fuses high-level semantic and local geometric features for each point, overcoming the limitations of token-based point-cloud reconstruction.

This paper proposes a fully automated data generation pipeline that generates pointwise perceptual distance labels between image pairs without any human annotation, and demonstrates that the diffusion trajectory aligns well with the human visual system.

A Coarse-to-Fine Scene Expert Network (C2FXNet) that achieves unified detection through hierarchical scene guidance through dual-level guidance mechanism, and enables robust multi-scene detection without scene-specific training.

A generalized Medical Imaging Disentanglement Learning framework that outperforms state-of-the-art supervised and self-supervised classification methods in accuracy across all datasets and successfully isolates target-specific latent representations.

Expensive pixel-level segmentation masks are unnecessary for fine-grained root phenotyping: parameter-efficient tuning of just 3.8% of a frozen DINOv3 ViT directly maps raw minirhizotron images to root traits with $R^2 \ge 0.93$.

This paper proposes SVEET, a framework that requires merely training on a pretrained bidirectional video diffusion model but supports high-quality streaming video editing in an auto-regressive fashion and proposes a decoupled training scheme that explicitly enforces the orthogonality between the optimization directions of video controllability and model causality.

This work proposes a novel approach under the more realistic black-box threat model that utilizes concepts from reinforcement learning to optimize perturbations with a non-differentiable target model, and shows the success of reinforcement learning inspired black-box adversarial attack (RIBA) in generating adversarial perturbations using only a small number of queries to the target model.

Results demonstrate that MVM provides a direct single-field parameterization of stochastic reverse dynamics while maintaining competitive generation quality.