Related papers: GridVAD: Open-Set Video Anomaly Detection via Spat…
Vision-Language Models (VLMs) have demonstrated strong performance on multimodal reasoning tasks, but their deployment remains challenging due to high inference latency and computational cost, particularly when processing high-resolution…
Vision-Language Models (VLMs) excel at 2D tasks such as grounding and captioning, yet remain limited in 3D understanding. A key limitation is their text-only supervision paradigm, which under-constrains fine-grained visual perception and…
Large Vision Language Models (LVLMs) have achieved significant progress in integrating visual and textual inputs for multimodal reasoning. However, a recurring challenge is ensuring these models utilize visual information as effectively as…
The reliability of a machine vision system for autonomous driving depends heavily on its training data distribution. When a vehicle encounters significantly different conditions, such as atypical obstacles, its perceptual capabilities can…
Unsupervised visual anomaly detection from multi-view images presents a significant challenge: distinguishing genuine defects from benign appearance variations caused by viewpoint changes. Existing methods, often designed for single-view…
Large Multimodal Models (LMMs) extend Large Language Models to the vision domain. Initial LMMs used holistic images and text prompts to generate ungrounded textual responses. Recently, region-level LMMs have been used to generate visually…
Video Anomaly Detection (VAD) aims to automatically analyze spatiotemporal patterns in surveillance videos collected from open spaces to detect anomalous events that may cause harm, such as fighting, stealing, and car accidents. However,…
Generative video models, a leading approach to world modeling, face fundamental limitations. They often violate physical and logical rules, lack interactivity, and operate as opaque black boxes ill-suited for building structured, queryable…
Video Anomaly Detection (VAD) serves as a pivotal technology in the intelligent surveillance systems, enabling the temporal or spatial identification of anomalous events within videos. While existing reviews predominantly concentrate on…
Visually-conditioned language models (VLMs) have seen growing adoption in applications such as visual dialogue, scene understanding, and robotic task planning; adoption that has fueled a wealth of new models such as LLaVa, InstructBLIP, and…
In robot scientific laboratories, visual anomaly detection is important for the timely identification and resolution of potential faults or deviations. It has become a key factor in ensuring the stability and safety of experimental…
Vision-Language Models (VLMs) are frequently undermined by object hallucination--generating content that contradicts visual reality--due to an over-reliance on linguistic priors. We introduce Positive-and-Negative Decoding (PND), a…
We study fine-grained referring image segmentation via a decoupled reason-then-segment pipeline. A vision-language model (VLM) receives an image and a natural-language query, reasons about the scene, and emits structured spatial prompts: a…
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…
Visual anomaly detection in multi-class settings poses significant challenges due to the diversity of object categories, the scarcity of anomalous examples, and the presence of camouflaged defects. In this paper, we propose PromptMAD, a…
Advances in ML have motivated the design of video analytics systems that allow for structured queries over video datasets. However, existing systems limit query expressivity, require users to specify an ML model per predicate, rely on…
Spatial reasoning is a fundamental aspect of human cognition, enabling intuitive understanding and manipulation of objects in three-dimensional space. While foundation models demonstrate remarkable performance on some benchmarks, they still…
Vision-Language Models (VLMs) demonstrate impressive capabilities across multimodal tasks, yet exhibit systematic spatial reasoning failures, achieving only 49% (CLIP) to 54% (BLIP-2) accuracy on basic directional relationships. For safe…
Accurately understanding and deciding high-level meta-actions is essential for ensuring reliable and safe autonomous driving systems. While vision-language models (VLMs) have shown significant potential in various autonomous driving tasks,…
While Vision-Language Models (VLMs) enable high-level semantic reasoning for end-to-end autonomous driving, particularly in unstructured environments, existing off-road datasets suffer from language annotations that are weakly aligned with…