arXiv:2607. 02269v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have demonstrated immense promise in Spatio-Temporal Video Grounding (STVG).
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: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...
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.
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."
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.
TempoGround is a vision‑language model–native framework for streaming visual grounding that detects cross‑frame object correspondence and explicitly models object presence states. It uses a curriculum prediction mechanism to resolve 2D instance association, predict object entry, continuation, or exit, decode 2D boxes, and lift them to 3D camera‑frame boxes. The approach is further refined with Streaming Grounding Reinforcement, which optimizes grounding, identity, and consistency rewards, and achieves significant improvements on multiple streaming visual grounding benchmarks.
arXiv:2512. 05277v3 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) are increasingly deployed as the perception and reasoning backbone of autonomous agents acting in the wild, with autonomous driving (AD) being one of the most safety-critical instances.
The paper introduces CamVLM, a framework that equips large vision‑language models with the ability to actively control camera viewpoints for improved surveillance video understanding. It presents two new datasets: CCTV‑Anomaly, a large‑scale surveillance video collection with detailed captions and event annotations, and CamTrack‑53K, an object‑centric viewpoint trajectory dataset for learning camera actions. Using reinforcement learning, CamVLM learns long‑horizon observation strategies, achieving state‑of‑the‑art performance in both passive and dynamic viewpoint settings.
AerialDojo-200K is a large-scale benchmark suite for open-world aerial object-goal search, featuring 42 simulation scenes across four families and 21 types, including urban, natural, infrastructure, and disaster environments. The dataset contains 205,732 task instances—over 100K semantic-goal and over 100K image-goal tasks—each with a collision-free reference trajectory and multi-view video recordings. A unified evaluation framework splits scenes into 21 in-distribution and 21 out-of-distribution sets, and preliminary tests on multimodal large language models show significant room for improvement in general-purpose aerial agents.
SYNCR is a synthetic benchmark designed to evaluate multimodal large language models on cross‑video reasoning. It contains 4,000 question‑answer pairs across 4,827 unique videos, covering tasks in temporal alignment, spatial tracking, comparative reasoning, and holistic synthesis. The benchmark reveals a significant performance gap between current models and humans, with models excelling at temporal ordering but struggling with precise physical and spatial reasoning.
arXiv:2604. 08991v3 Announce Type: replace-cross Abstract: Reliable embodied interaction in indoor environments requires agents to precisely localize small everyday objects from visual observations.