Computer Vision - Weekly Roundup

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.

AdvScene, a conditional latent diffusion model that is trained in two stages that Conditioning on ego driving displacement prevents the ego from remaining static, and RL finetuning induces criticality directly with non-differentiable safety-critical metrics is proposed.

Findings indicate that Federated Learning is a safe and efficient solution to AI-assisted diagnosis in contemporary healthcare when combined with the use of sophisticated object detection models.

A hybrid approach that draws on the stability and generation quality of denoising diffusion models, which yields a stable training process and generates microstructures of varying complexity with minimal slice artefacts and close agreement with ground-truth phase fractions and structural descriptors.

PointEvent is proposed, a lightweight event-wise state-space framework that alternates serialized scans across the complementary orders, progressively consolidating fragmented motion evidence beyond fixed local neighborhoods, and achieves SOTA with the fewest parameters and fastest measured inference among the compared methods.

DART, a training-free method that combines low-rank coordinate transport with target-schedule response calibration with forward evaluations and no source training videos is proposed, and Adapter-level results reveal positive functional effects for some adapters and strong attenuation with reduced negative functional effects for others.

PACE (Precise AI Cinematic Expression), a typed representation for the plan: the screenplay evidence, the characters, props and locations it needs, where each subject stands, and what the camera does.

BinoGen is presented, an automated framework for generating large-scale, embodiment-aware egocentric binocular visual experiences in indoor environments and incorporating BinoGen data consistently improves real-world visual perception, including depth estimation, object detection, and video object tracking.

SeetaPsych v1.0 is presented, an open source, unified and extensible computer vision toolkit designed to extract psychologically relevant signals from facial images and/or face based videos to offer an integrated and accessible visual measurement platform for research in psychology, behavioral science, human computer interaction, and related fields.

A task-oriented framework that bypasses image reconstruction and directly transmits semantic features extracted by a multitask-pretrained backbone is investigated, with the largest improvements in the low-SNR regime.

NeuSOGA3D (Neuro-Symbolic Geometric Abstraction in 3D), a hybrid framework that combines learned perceptual priors inherited from NeuSOGA with explicit symbolic geometric reasoning for explainable geometric intelligence, is presented.

G^2RA-Net is proposed, a medical image segmentation framework that combines graph-based cross-slice relation modeling with atten- tion gating that outperforms representative methods in accuracy and boundary quality.

CrossUAV is introduced, a UAV benchmark for joint object detection and instance segmentation that provides a unified evaluation platform for cross-granularity task collaboration and Cross-Granularity Socialized Collaboration is proposed, a progressive and adaptive framework that regulates when, where, and how tasks exchange information across network hierarchies.

Graph-Guided Token Merging (G2TM) is extended, a single module inserted early in a ViT-based network, beyond its original Segmenter setting, and its behavior and accuracy-efficiency trade-off are consistent across every tested architecture for a given backbone size, indicating that its effectiveness is a property of the encoder rather than the decoder.

CapMap-MS-TTA is presented, a training-free submission built on Microsoft Florence-2-base, combining caption keyword mapping with multi-scale flip test-time augmentation, and ranks 3rd on the final MUMU leaderboard.

CamoShift is the first to target both visual stealthiness and attack success in visible-infrared object detection, and is the first to target both visual stealthiness and attack success in visible-infrared object detection.

ACT is the first framework to study semi-supervised VIOD under this image-pair-level setting and forms consensus pseudo labels under pair-preserving views to recover branch-wise misses and supervise unlabeled pairs.

Inspired by iterative error feedback in structured prediction, FAPR represents the current segmentation mask as a dynamic failure state and models each repair operation as a state-transition operator, enabling later operations to adapt to preceding changes.

A fully automatic multi-signal release frame detection (MS-RFD) method for hammer throw using reconstructed 3D hammer trajectories and shows that speed dynamics and radial expansion provide the strongest signals for release frame detection, while angular velocity and post-release linearity provide smaller refinements.

This work proposes a latency-aware metric for multi-object tracking called streaming-HOTA (s-HOTA), and introduces an ultra-High-resolution Airborne Remote-sensing Dataset (HARD) annotated at three levels for object detection, multi-object tracking, and scene-level visual question answering.

Efficient Unified Multimodal Understanding (EUMU), the winning solution for the MUMU Track of the 8th LSVOS Challenge, builds on a shared pretrained multimodal model, using its prompt-based capabilities for detection and captioning and training lightweight heads on shared visual features to predict quality, scene, and event tags.