Related papers: Multi-Modal Motion Retrieval by Learning a Fine-Gr…
Long-form video understanding presents significant challenges for interactive retrieval systems, as conventional methods struggle to process extensive video content efficiently. Existing approaches often rely on single models, inefficient…
Learning from multiple modalities, such as audio and video, offers opportunities for leveraging complementary information, enhancing robustness, and improving contextual understanding and performance. However, combining such modalities…
Video understanding plays a fundamental role for content moderation on short video platforms, enabling the detection of inappropriate content. While classification remains the dominant approach for content moderation, it often struggles in…
In this paper, we present TMR, a simple yet effective approach for text to 3D human motion retrieval. While previous work has only treated retrieval as a proxy evaluation metric, we tackle it as a standalone task. Our method extends the…
Cross-modal retrieval has drawn much attention in both computer vision and natural language processing domains. With the development of convolutional and recurrent neural networks, the bottleneck of retrieval across image-text modalities is…
Fine-grained video classification requires understanding complex spatio-temporal and semantic cues that often exceed the capacity of a single modality. In this paper, we propose a multimodal framework that fuses video, image, and text…
In this work, we present MoLang (a Motion-Language connecting model) for learning joint representation of human motion and language, leveraging both unpaired and paired datasets of motion and language modalities. To this end, we propose a…
Recent multimodal retrieval methods have endowed text-based retrievers with multimodal capabilities by utilizing pre-training strategies for visual-text alignment. They often directly fuse the two modalities for cross-reference during the…
Image-text retrieval requires the system to bridge the heterogenous gap between vision and language for accurate retrieval while keeping the network lightweight-enough for efficient retrieval. Existing trade-off solutions mainly study from…
Human motion generation is essential for fields such as animation, robotics, and virtual reality, requiring models that effectively capture motion dynamics from text descriptions. Existing approaches often rely on Contrastive Language-Image…
Videos contain multi-modal content, and exploring multi-level cross-modal interactions with natural language queries can provide great prominence to text-video retrieval task (TVR). However, new trending methods applying large-scale…
Recent advancements in foundation models for 2D vision have substantially improved the analysis of dynamic scenes from monocular videos. However, despite their strong generalization capabilities, these models often lack 3D consistency, a…
Current state-of-the-art approaches to cross-modal retrieval process text and visual input jointly, relying on Transformer-based architectures with cross-attention mechanisms that attend over all words and objects in an image. While…
We aim to learn a joint representation between inertial measurement unit (IMU) signals and 2D pose sequences extracted from video, enabling accurate cross-modal retrieval, temporal synchronization, subject and body-part localization, and…
Recent advances have been witnessed in audio-language joint learning, such as CLAP, that shows much success in multi-modal understanding tasks. These models usually aggregate uni-modal local representations, namely frame or word features,…
Multimodal emotion recognition utilizes complete multimodal information and robust multimodal joint representation to gain high performance. However, the ideal condition of full modality integrity is often not applicable in reality and…
Online video web content is richly multimodal: a single video blends vision, speech, ambient audio, and on-screen text. Retrieval systems typically treat these modalities as independent retrieval sources, which can lead to noisy and subpar…
As medical diagnoses increasingly leverage multimodal data, machine learning models are expected to effectively fuse heterogeneous information while remaining robust to missing modalities. In this work, we propose a novel multimodal…
Background music (BGM) can enhance the video's emotion. However, selecting an appropriate BGM often requires domain knowledge. This has led to the development of video-music retrieval techniques. Most existing approaches utilize pretrained…
We present Omni-Embed-Nemotron, a unified multimodal retrieval embedding model developed to handle the increasing complexity of real-world information needs. While Retrieval-Augmented Generation (RAG) has significantly advanced language…