相关论文: Video-STAR: Reinforcing Open-Vocabulary Action Rec…
Human action recognition often struggles with deep semantic understanding, complex contextual information, and fine-grained distinction, limitations that traditional methods frequently encounter when dealing with diverse video data.…
Utilizing vision and language models (VLMs) pre-trained on large-scale image-text pairs is becoming a promising paradigm for open-vocabulary visual recognition. In this work, we extend this paradigm by leveraging motion and audio that…
Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities across diverse tasks, yet they lag significantly behind humans in spatial reasoning. We investigate this gap through Transformation-Driven Visual Reasoning…
Video Question Answering (VideoQA) task serves as a critical playground for evaluating whether foundation models can effectively perceive, understand, and reason about dynamic real-world scenarios. However, existing Multimodal Large…
Recent progress in reasoning capabilities of Multimodal Large Language Models(MLLMs) has highlighted their potential for performing complex video understanding tasks. However, in the domain of Video Anomaly Detection and Understanding…
Human processes video reasoning in a sequential spatio-temporal reasoning logic, we first identify the relevant frames ("when") and then analyse the spatial relationships ("where") between key objects, and finally leverage these…
Multimodal Large Reasoning Models (MLRMs) have achieved remarkable strides in visual reasoning through test time compute scaling, yet long chain reasoning remains prone to hallucinations. We identify a concerning phenomenon termed the…
Pre-trained vision-language models (VLMs) have enabled significant progress in open vocabulary computer vision tasks such as image classification, object detection and image segmentation. Some recent works have focused on extending VLMs to…
Predicting and reasoning how a video would make a human feel is crucial for developing socially intelligent systems. Although Multimodal Large Language Models (MLLMs) have shown impressive video understanding capabilities, they tend to…
Spatio-temporal action detection (STAD) is an important fine-grained video understanding task. Current methods require box and label supervision for all action classes in advance. However, in real-world applications, it is very likely to…
Action detection aims to detect (recognize and localize) human actions spatially and temporally in videos. Existing approaches focus on the closed-set setting where an action detector is trained and tested on videos from a fixed set of…
Multimodal emotion recognition is a task of great concern. However, traditional data sets are based on fixed labels, resulting in models that often focus on main emotions and ignore detailed emotional changes in complex scenes. This report…
Existing semi-supervised video anomaly detection (VAD) methods often struggle with detecting complex anomalies involving object interactions and generally lack explainability. To overcome these limitations, we propose a novel VAD framework…
The performance of Large Vision Language Models (LVLMs) is dependent on the size and quality of their training datasets. Existing video instruction tuning datasets lack diversity as they are derived by prompting large language models with…
Multimodal Large Language Models (MLLMs) have achieved impressive progress in vision-language alignment, yet they remain limited in visual-spatial reasoning. We first identify that this limitation arises from the attention mechanism: visual…
Open-source multimodal large language models (MLLMs) excel in various tasks involving textual and visual inputs but still struggle with complex multimodal mathematical reasoning, lagging behind proprietary models like GPT-4V(ision) and…
Multimodal Large Language Models (MLLMs) frequently hallucinate due to their reliance on fragile, linear reasoning and weak visual grounding. We propose Visual Attention Reasoning (VAR), a reinforcement learning framework that reformulates…
Despite an exciting new wave of multimodal machine learning models, current approaches still struggle to interpret the complex contextual relationships between the different modalities present in videos. Going beyond existing methods that…
The remarkable reasoning capability of large language models (LLMs) stems from cognitive behaviors that emerge through reinforcement with verifiable rewards. This work investigates how to transfer this principle to Multimodal LLMs (MLLMs)…
Multimodal large language models (MLLMs) play a pivotal role in advancing the quest for general artificial intelligence. However, achieving unified target for multimodal understanding and generation remains challenging due to optimization…