Related papers: FingerCap: Fine-grained Finger-level Hand Motion C…
While Multimodal Large Language Models (MLLMs) have experienced rapid advancements, their visual encoders frequently remain a performance bottleneck. Conventional CLIP-based encoders struggle with dense spatial tasks due to the loss of…
Action understanding has evolved into the era of fine granularity, as most human behaviors in real life have only minor differences. To detect these fine-grained actions accurately in a label-efficient way, we tackle the problem of…
Fine-grained video action recognition can be conceptualized as a video-text matching problem. Previous approaches often rely on global video semantics to consolidate video embeddings, which can lead to misalignment in video-text pairs due…
Existing music captioning methods are limited to generating concise global descriptions of short music clips, which fail to capture fine-grained musical characteristics and time-aware musical changes. To address these limitations, we…
Markerless motion capture and understanding of professional non-daily human movements is an important yet unsolved task, which suffers from complex motion patterns and severe self-occlusion, especially for the monocular setting. In this…
Vision-language models such as CLIP have shown impressive capabilities in aligning images and text, but they often struggle with lengthy and detailed text descriptions due to pre-training on short and concise captions. We present FAST-GOAL…
Existing Video Corpus Moment Retrieval (VCMR) is limited to coarse-grained understanding, which hinders precise video moment localization when given fine-grained queries. In this paper, we propose a more challenging fine-grained VCMR…
Current video models fail as world model as they lack fine-graiend control. General-purpose household robots require real-time fine motor control to handle delicate tasks and urgent situations. In this work, we introduce fine-grained…
As a pioneering vision-language model, CLIP (Contrastive Language-Image Pre-training) has achieved significant success across various domains and a wide range of downstream vision-language tasks. However, the text encoders in popular CLIP…
Large Multimodal Models (LMMs) have achieved significant progress by extending large language models. Building on this progress, the latest developments in LMMs demonstrate the ability to generate dense pixel-wise segmentation through the…
Large Language Models (LLMs) demonstrate remarkable proficiency in comprehending and handling text-based tasks. Many efforts are being made to transfer these attributes to video modality, which are termed Video-LLMs. However, existing…
Privacy-preserving semantic understanding of human activities is important for indoor sensing, yet existing Wi-Fi CSI-based systems mainly focus on pose estimation or predefined action classification rather than fine-grained language…
We present CAT-V (Caption AnyThing in Video), a training-free framework for fine-grained object-centric video captioning that enables detailed descriptions of user-selected objects through time. CAT-V integrates three key components: a…
Image captioning has become an important task in computer vision, enabling models to generate natural language descriptions of visual content. While several datasets exist for natural images and high-resolution optical remote sensing…
Realistic Hand manipulation is a key component of immersive virtual reality (VR), yet existing methods often rely on kinematic approach or motion-capture datasets that omit crucial physical attributes such as contact forces and finger…
Contrastively pretrained audio-language models (e.g., CLAP) excel at clip-level understanding but struggle with frame-level tasks. Existing extensions fail to exploit the varying granularity of real-world audio-text data, where massive…
Despite the success of Vision-Language Models (VLMs) like CLIP in aligning vision and language, their proficiency in detailed, fine-grained visual comprehension remains a key challenge. We present CLIP-IN, a novel framework that bolsters…
We address the problem of fine-grained action localization from temporally untrimmed web videos. We assume that only weak video-level annotations are available for training. The goal is to use these weak labels to identify temporal segments…
Video captioning aims to generate comprehensive and coherent descriptions of the video content, contributing to the advancement of both video understanding and generation. However, existing methods often suffer from motion-detail imbalance,…
Videos are more informative than images because they capture the dynamics of the scene. By representing motion in videos, we can capture dynamic activities. In this work, we introduce GPT-4 generated motion descriptions that capture…