Related papers: Leveraging VLM-Based Pipelines to Annotate 3D Obje…

Open-set perception in complex traffic environments poses a critical challenge for autonomous driving systems, particularly in identifying previously unseen object categories, which is vital for ensuring safety. Visual Language Models…

Vision-Language Models (VLMs) have demonstrated strong capability in a wide range of tasks such as visual recognition, document parsing, and visual grounding. Nevertheless, recent work shows that while VLMs often manage to capture the…

Vision-Language Models (VLMs) have transformed tasks requiring visual and reasoning abilities, such as image retrieval and Visual Question Answering (VQA). Despite their success, VLMs face significant challenges with tasks involving…

Visual Language Models (VLMs) are often used for zero-shot detection of visual attributes in the image. We present a zero-shot evaluation of open-source VLMs for privacy-related attribute recognition. We identify the attributes for which…

Multimodal Large Language Models (MLLMs) such as GPT-4V and Gemini Pro face challenges in achieving human-level perception in Visual Question Answering (VQA), particularly in object-oriented perception tasks which demand fine-grained…

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…

As multimodal language models advance, their application to 3D scene understanding is a fast-growing frontier, driving the development of 3D Vision-Language Models (VLMs). Current methods show strong dependence on object detectors,…

Vision-language models (VLMs) excel at image-text retrieval yet persistently fail at compositional reasoning, distinguishing captions that share the same words but differ in relational structure. We present, a unified evaluation and…

Inspired by human categorization, object property reasoning involves identifying and recognizing low-level details and higher-level abstractions. While current visual question answering (VQA) studies consider multiple object properties,…

Counting the number of items in a visual scene remains a fundamental yet challenging task in computer vision. Traditional approaches to solving this problem rely on domain-specific counting architectures, which are trained using datasets…

The success of VLMs often relies on the dynamic high-resolution schema that adaptively augments the input images to multiple crops, so that the details of the images can be retained. However, such approaches result in a large number of…

Open-vocabulary object detection (OVD) aims to recognize and localize object categories beyond the training set. Recent approaches leverage vision-language models to generate pseudo-labels using image-text alignment, allowing detectors to…

Rare-object detection remains a challenging task in autonomous driving systems, particularly when relying solely on point cloud data. Although Vision-Language Models (VLMs) exhibit strong capabilities in image understanding, their potential…

The rapidly developing Large Vision Language Models (LVLMs) have shown notable capabilities on a range of multi-modal tasks, but still face the hallucination phenomena where the generated texts do not align with the given contexts,…

Vision-Language Pre-training (VLP) has advanced the performance of many vision-language tasks, such as image-text retrieval, visual entailment, and visual reasoning. The pre-training mostly utilizes lexical databases and image queries in…

Gaze understanding unifies the detection of people, their gaze targets, and objects of interest into a single framework, offering critical insight into visual attention and intent estimation. Although prior research has modelled gaze cues…

Vision language models (VLMs) have shown impressive capabilities across a variety of tasks, from logical reasoning to visual understanding. This opens the door to richer interaction with the world, for example robotic control. However, VLMs…

Concept-bottleneck models (CBMs) are neural classifiers that compute predictions from high-level concepts extracted from the input. CBMs ensure stakeholders can understand the concepts -- and the predictions they entail -- by learning these…

Continual learning enables pre-trained generative vision-language models (VLMs) to incorporate knowledge from new tasks without retraining data from previous ones. Recent methods update a visual projector to translate visual information for…

Vision-based quality assessment in additive manufacturing often requires dedicated machine learning models and application-specific datasets. However, data collection and model training can be expensive and time-consuming. In this paper, we…