Related papers: Locality-aware Cross-modal Correspondence Learning…
Cross-view object geo-localization has recently gained attention due to potential applications. Existing methods aim to capture spatial dependencies of query objects between different views through attention mechanisms to obtain spatial…
In recent years, there have been numerous developments towards solving multimodal tasks, aiming to learn a stronger representation than through a single modality. Certain aspects of the data can be particularly useful in this case - for…
Although person or identity verification has been predominantly explored using individual modalities such as face and voice, audio-visual fusion has recently shown immense potential to outperform unimodal approaches. Audio and visual…
High temporal resolution is essential for capturing fine-grained details in video understanding. However, current video large language models (VLLMs) and benchmarks mostly rely on low-frame-rate sampling, such as uniform sampling or…
While Multimodal Large Language Models (MLLMs) excel in general vision-language tasks, their application to remote sensing change understanding is hindered by a fundamental "temporal blindness". Existing architectures lack intrinsic…
Positional encoding is essential for large language models (LLMs) to represent sequence order, yet recent studies show that Rotary Position Embedding (RoPE) can induce massive activation. We investigate the source of these instabilities via…
Multimodal semantic communication, which integrates various data modalities such as text, images, and audio, significantly enhances communication efficiency and reliability. It has broad application prospects in fields such as artificial…
Motion prediction is critical for autonomous vehicles to effectively navigate complex environments and accurately anticipate the behaviors of other traffic participants. As autonomous driving continues to evolve, the need to assimilate new…
In video Multimodal Large Language Models (video MLLMs), the visual encapsulation process plays a pivotal role in converting video contents into representative tokens for LLM input. While linear projectors are widely employed for…
Cross-view object geo-localization enables high-precision object localization through cross-view matching, with critical applications in autonomous driving, urban management, and disaster response. However, existing methods rely on…
3D visual grounding aims to identify objects in 3D point cloud scenes that match specific natural language descriptions. This requires the model to not only focus on the target object itself but also to consider the surrounding environment…
Recent development in vision-language approaches has instigated a paradigm shift in learning visual recognition models from language supervision. These approaches align objects with language queries (e.g. "a photo of a cat") and improve the…
In this paper, we show how to use audio to supervise the learning of active speaker detection in video. Voice Activity Detection (VAD) guides the learning of the vision-based classifier in a weakly supervised manner. The classifier uses…
Recent advances in Large Language Models (LLMs) have led to significant breakthroughs in video understanding. However, existing models still struggle with long video processing due to the context length constraint of LLMs and the vast…
Temporal moment localization aims to retrieve the best video segment matching a moment specified by a query. The existing methods generate the visual and semantic embeddings independently and fuse them without full consideration of the…
Deep learning has successfully shown excellent performance in learning joint representations between different data modalities. Unfortunately, little research focuses on cross-modal correlation learning where temporal structures of…
Large multimodal models (LMMs) excel in scene understanding but struggle with fine-grained spatiotemporal reasoning due to weak alignment between linguistic and visual representations. Existing methods map textual positions and durations…
Neuromorphic vision sensors, commonly referred to as event cameras, generate a massive number of pixel-level events, composed by spatiotemporal and polarity information, thus demanding highly efficient coding solutions. Existing solutions…
This report presents our systems submitted to the audio-only and audio-visual tracks of the DCASE2025 Task 3 Challenge: Stereo Sound Event Localization and Detection (SELD) in Regular Video Content. SELD is a complex task that combines…
Many motion-centric video analysis tasks, such as atomic actions, detecting atypical motor behavior in individuals with autism, or analyzing articulatory motion in real-time MRI of human speech, require efficient and interpretable temporal…