Related papers: ToG-Bench: Task-Oriented Spatio-Temporal Grounding…
Temporal Video Grounding (TVG), which requires pinpointing relevant temporal segments from video based on language query, has always been a highly challenging task in the field of video understanding. Videos often have a larger volume of…
Given some video-query pairs with untrimmed videos and sentence queries, temporal sentence grounding (TSG) aims to locate query-relevant segments in these videos. Although previous respectable TSG methods have achieved remarkable success,…
In the context of human-robot interaction and collaboration scenarios, robotic grasping still encounters numerous challenges. Traditional grasp detection methods generally analyze the entire scene to predict grasps, leading to redundancy…
Grounding natural language in 3D environments is a critical step toward achieving robust 3D vision-language alignment. Current datasets and models for 3D visual grounding predominantly focus on identifying and localizing objects from…
Video understanding tasks take many forms, from action detection to visual query localization and spatio-temporal grounding of sentences. These tasks differ in the type of inputs (only video, or video-query pair where query is an image…
Vision-language foundation models have shown impressive capabilities across various zero-shot tasks, including training-free localization and grounding, primarily focusing on localizing objects in images. However, leveraging those…
Spatio-Temporal Video Grounding (STVG) aims to localize a spatio-temporal tube that corresponds to a given language query in an untrimmed video. This is a challenging task since it involves complex vision-language understanding and…
Models like OpenAI-o3 pioneer visual grounded reasoning by dynamically referencing visual regions, just like human "thinking with images". However, no benchmark exists to evaluate these capabilities holistically. To bridge this gap, we…
The enhancement of generalization in robots by large vision-language models (LVLMs) is increasingly evident. Therefore, the embodied cognitive abilities of LVLMs based on egocentric videos are of great interest. However, current datasets…
Video temporal grounding (VTG) is a fine-grained video understanding problem that aims to ground relevant clips in untrimmed videos given natural language queries. Most existing VTG models are built upon frame-wise final-layer CLIP…
Temporal Action Detection and Moment Retrieval constitute two pivotal tasks in video understanding, focusing on precisely localizing temporal segments corresponding to specific actions or events. Recent advancements introduced Moment…
While recent video world models can generate highly realistic videos, their ability to perform semantic reasoning and planning remains unclear and unquantified. We introduce Target-Bench, the first benchmark that enables comprehensive…
Spatial-Temporal Video Grounding (STVG) is a challenging task which aims to localize the spatio-temporal tube of the interested object semantically according to a natural language query. Most previous works not only severely rely on the…
Multimodal Large Language Models (MLLMs) have shown strong performance on Video Temporal Grounding (VTG). However, their coarse recognition capabilities are insufficient for fine-grained temporal understanding, making task-specific…
Learning commonsense reasoning from visual contexts and scenes in real-world is a crucial step toward advanced artificial intelligence. However, existing video reasoning benchmarks are still inadequate since they were mainly designed for…
To enable progress towards egocentric agents capable of understanding everyday tasks specified in natural language, we propose a benchmark and a synthetic dataset called Egocentric Task Verification (EgoTV). The goal in EgoTV is to verify…
Visual entity tracking is an innate cognitive ability in humans, yet it remains a critical bottleneck for Vision-Language Models (VLMs). This deficit is often obscured in existing video benchmarks by visual shortcuts. We introduce…
The burgeoning field of Artificial Intelligence Generated Content (AIGC) is witnessing rapid advancements, particularly in video generation. This paper introduces AIGCBench, a pioneering comprehensive and scalable benchmark designed to…
Procedural activities are fundamentally driven by object state transitions, yet existing instructional video benchmarks remain action-centric and cannot evaluate whether models reason about how objects evolve toward task completion. In this…
In vision-language models (VLMs), misalignment between textual descriptions and visual coordinates often induces hallucinations. This issue becomes particularly severe in dense prediction tasks such as spatial-temporal video grounding…