相关论文: SVAG-Bench: A Large-Scale Benchmark for Multi-Inst…
Robots collaborating with humans must convert natural language goals into actionable, physically grounded decisions. For example, executing a command such as "go two meters to the right of the fridge" requires grounding semantic references,…
Spatio-temporal video grounding (STVG) requires localizing a target object in untrimmed videos both temporally and spatially from natural language descriptions. Despite their strong language understanding, multimodal large language models…
Multimodal AI agents are increasingly automating complex real-world workflows that involve online web execution. However, current web-agent benchmarks suffer from a critical limitation: they focus entirely on web-based interaction and…
We propose a new task and model for dense video object captioning -- detecting, tracking and captioning trajectories of objects in a video. This task unifies spatial and temporal localization in video, whilst also requiring fine-grained…
Achieving Artificial General Intelligence (AGI) requires agents that learn and interact adaptively, with interactive world models providing scalable environments for perception, reasoning, and action. Yet current research still lacks…
Spatio-temporal localization is vital for precise interactions across diverse domains, from biological research to autonomous navigation and interactive interfaces. Current video-based approaches, while proficient in tracking, lack the…
Visual Grounding (VG) aims to localize specific objects in an image according to natural language expressions, serving as a fundamental task in vision-language understanding. However, existing VG benchmarks are mostly derived from datasets…
With the rapid advancement of text-conditioned Video Generation Models (VGMs), the quality of generated videos has significantly improved, bringing these models closer to functioning as ``*world simulators*'' and making real-world-level…
Temporal grounding of text descriptions in videos is a central problem in vision-language learning and video understanding. Existing methods often prioritize accuracy over scalability -- they have been optimized for grounding only a few…
Understanding fine-grained temporal dynamics is crucial for multimodal video comprehension and generation. Due to the lack of fine-grained temporal annotations, existing video benchmarks mostly resemble static image benchmarks and are…
Video reasoning models are a core component of egocentric and embodied agents. However, standard benchmarks for assessing models provide only evaluation of the output (e.g. the answer to a question), without evaluation of intermediate…
This paper does not introduce a novel method but instead establishes a straightforward, incremental, yet essential baseline for video temporal grounding (VTG), a core capability in video understanding. While multimodal large language models…
Systems that can find correspondences between multiple modalities, such as between speech and images, have great potential to solve different recognition and data analysis tasks in an unsupervised manner. This work studies multimodal…
Recent progress in generative video models, such as Veo-3, has shown surprising zero-shot reasoning abilities, creating a growing need for systematic and reliable evaluation. We introduce V-ReasonBench, a benchmark designed to assess video…
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…
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,…
Understanding videos inherently requires reasoning over both visual and auditory information. To properly evaluate Omni-Large Language Models (Omni-LLMs), which are capable of processing multi-modal information including vision and audio,…
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…
Temporal understanding in autonomous driving (AD) remains a significant challenge, even for recent state-of-the-art (SoTA) Vision-Language Models (VLMs). Prior work has introduced datasets and benchmarks aimed at improving temporal…
Characterizing and quantifying gender representation disparities in audiovisual storytelling contents is necessary to grasp how stereotypes may perpetuate on screen. In this article, we consider the high-level construct of objectification…