Related papers: MASH-VLM: Mitigating Action-Scene Hallucination in…

Large Language Models (LLMs) have strong instruction-following capability to interpret and execute tasks as directed by human commands. Multimodal Large Language Models (MLLMs) have inferior instruction-following ability compared to LLMs.…

Multimodal large language models (MLLMs) have revolutionized cross-modal understanding but continue to struggle with hallucinations - fabricated content contradicting visual inputs. Existing hallucination mitigation methods either incur…

The core challenge in video understanding lies in perceiving dynamic content changes over time. However, multimodal large language models struggle with temporal-sensitive video tasks, which requires generating timestamps to mark the…

Recently, rapid advancements have been made in multimodal large language models (MLLMs), especially in video understanding tasks. However, current research focuses on simple video scenarios, failing to reflect the complex and diverse nature…

Spatial relation hallucinations pose a persistent challenge in large vision-language models (LVLMs), leading to generate incorrect predictions about object positions and spatial configurations within an image. To address this issue, we…

Understanding social interaction in video requires reasoning over a dynamic interplay of verbal and non-verbal cues: who is speaking, to whom, and with what gaze or gestures. While Multimodal Large Language Models (MLLMs) are natural…

Continuous sign language recognition (CSLR) requires precise spatio-temporal modeling to accurately recognize sequences of gestures in videos. Existing frameworks often rely on CNN-based spatial backbones combined with temporal convolution…

Existing benchmarks for Vision-Language Models (VLMs) primarily evaluate spatio-temporal understanding on simple single-action videos, closed attribute sets and restricted entity types, failing to capture the freeform, multi-action…

Temporal action localization (TAL) requires recognizing the target event and localizing its start and end times precisely in untrimmed videos. Recent vision-language formulations improve semantic reasoning and support language-conditioned…

Vision-Language Models (VLMs) are increasingly used in safety-critical applications that require reliable visual grounding. However, these models often hallucinate details that are not present in the image to satisfy user prompts. While…

Hallucinations in vision-language models (VLMs) hinder reliability and real-world applicability, usually stemming from distribution shifts between pretraining data and test samples. Existing solutions, such as retraining or fine-tuning on…

Vision-Language Models (VLMs) are becoming increasingly popular in the medical domain, bridging the gap between medical images and clinical language. Existing VLMs demonstrate an impressive ability to comprehend medical images and text…

Localizing unusual activities, such as human errors or surveillance incidents, in videos holds practical significance. However, current video understanding models struggle with localizing these unusual events likely because of their…

Video large language models (VideoLLMs) show strong capability in video understanding, yet long-context inference is still dominated by massive redundant visual tokens in the prefill stage. We revisit token compression for VideoLLMs under a…

Due to the auto-regressive nature of current video large language models (Video-LLMs), the inference latency increases as the input sequence length grows, posing challenges for the efficient processing of video sequences that are usually…

Object level hallucination remains a central reliability challenge for vision language models (VLMs), particularly in binary object existence verification. Existing benchmarks emphasize aggregate accuracy but rarely disentangle whether…

Large Vision-Language Models (LVLMs) achieve strong performance on many multimodal tasks, but object hallucinations severely undermine their reliability. Most existing studies focus on the text modality, attributing hallucinations to overly…

Leveraging large-scale Text-to-Image (TTI) models have become a common technique for generating exemplar or training dataset in the fields of image synthesis, video editing, 3D reconstruction. However, semantic structural visual…

Large Language Models (LLMs) are increasingly deployed in safety-critical domains, yet remain susceptible to hallucinations. While prior works have proposed confidence representation methods for hallucination detection, most of these…

Deep learning models have enjoyed great success for image related computer vision tasks like image classification and object detection. For video related tasks like human action recognition, however, the advancements are not as significant…