arXiv Computer Vision
VANTAGE-Bench: Evaluating the Infrastructure AI Gap in Vision-Language Models
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv AI
Jul 3
AnyGroundBench: A Specialized-Domain Benchmark for Video Grounding in Vision-Language Models
arXiv:2607. 02269v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have demonstrated immense promise in Spatio-Temporal Video Grounding (STVG).
arXiv Computer Vision
Sep 17
Understanding Dynamic Scenes at Gigapixel Scale: Wide-Area Spatio-Temporal Perception from UAVs
The paper introduces the Wide-area Spatio-temporal Scene Understanding (WSTU) problem, which demands simultaneous wide-area coverage, per-target resolution, and temporal continuity—capabilities lacking in existing datasets. To address this, the authors present HARD, an ultra‑high‑resolution (12768×9564) UAV dataset annotated for object detection, multi‑object tracking, and scene‑level visual question answering. They also propose a latency‑aware metric, streaming‑HOTA (s‑HOTA), and show through baseline experiments that high resolution and processing latency significantly impact detection, tracking, and VQA performance, revealing gaps in current methods for WSTU.
arXiv AI
Oct 21
OPIS: An Input-Grounded Benchmark for Multi-Object Memory in Video World Models
arXiv:2609.35052v2 Announce Type: replace-cross Abstract: Video world models must preserve the visual state of the world over time, but existing evaluation protocols often rely on generated histories...
arXiv Computer Vision
Sep 4
ORMOT: A Dataset and Framework for Omnidirectional Referring Multi-Object Tracking
The paper introduces ORMOT, a new task that extends Referring Multi‑Object Tracking to omnidirectional 360° imagery, ensuring full scene context for language‑guided tracking. It presents ORSet, a dataset of 27 omnidirectional scenes with 848 language descriptions and 3,401 annotated objects, and introduces ORTrack, an LVLM‑driven framework that performs zero‑shot detection and robust cross‑frame association. Experiments on ORSet show that ORTrack achieves state‑of‑the‑art performance, establishing a strong baseline for future research.
arXiv Computer Vision
2d ago
GTASA: Ground Truth Annotations for Spatiotemporal Analysis, Evaluation and Training of Video Models
GTASA: Ground Truth Annotations for Spatiotemporal Analysis, Evaluation and Training of Video Models presents GEST-Engine, an open‑source system that deterministically renders multi‑actor video scenarios while recording exhaustive ground truth—including 3D entity and camera states, pairwise spatial relations, event‑to‑frame mappings, instance segmentation, and long descriptions—at no extra annotation cost. The authors release a 938‑video dataset, GTASA, which offers the densest spatial‑relation coverage of any video dataset, with an entity‑pair relation graph at every frame that is roughly 84× denser than current state‑of‑the‑art collections. They demonstrate the dataset’s value by showing that pretraining on GTASA improves VideoLLaMA3 captioning, and by using it to probe frozen video encoders on 11 spatio‑temporal tasks, revealing that relational understanding remains near chance. whyItMatters":"The dataset provides a uniquely dense, exact 3D ground truth for spatio‑temporal video analysis, enabling measurable progress in training and evaluating video models on relational reasoning tasks."
arXiv Computer Vision
Oct 7
FindIt: A Format-Informed Visual Detection Benchmark for Generalist Multimodal LLMs
The paper introduces FindIt, the first comprehensive benchmark for evaluating the promptable localization abilities of generalist multimodal large language models (MLLMs). It covers four core task categories—object detection, referring expression detection, instance-level detection, and video-based detection—and provides a unified framework that standardizes inputs, enforces parsable bounding box outputs, and defines transparent evaluation protocols. Using this benchmark, the authors assess a range of open-source and proprietary MLLMs, revealing both their strengths and limitations, particularly their sensitivity to formatting constraints and difficulty generalizing to minor variations.