Related papers: Spatial-Temporal Graph Mamba for Music-Guided Danc…

In the field of multimodal medical data analysis, leveraging diverse types of data and understanding their hidden relationships continues to be a research focus. The main challenges lie in effectively modeling the complex interactions…

Magnetic resonance (MR)-to-computed tomography (CT) translation offers significant advantages, including the elimination of radiation exposure associated with CT scans and the mitigation of imaging artifacts caused by patient motion. The…

Due to recent advances in pose-estimation methods, human motion can be extracted from a common video in the form of 3D skeleton sequences. Despite wonderful application opportunities, effective and efficient content-based access to large…

Mamba has recently emerged as a promising alternative to Transformers, offering near-linear complexity in processing sequential data. However, while channels in time series (TS) data have no specific order in general, recent studies have…

This paper introduces Bio-Inspired Mamba (BIM), a novel online learning framework for selective state space models that integrates biological learning principles with the Mamba architecture. BIM combines Real-Time Recurrent Learning (RTRL)…

Recently, the Mamba architecture based on state space models has demonstrated remarkable performance in a series of natural language processing tasks and has been rapidly applied to remote sensing change detection (CD) tasks. However, most…

Temporal human action detection aims to identify and localize action segments within untrimmed videos, serving as a pivotal task in video understanding. Despite the progress achieved by prior architectures like CNN and Transformer models,…

We present Split-then-Merge (StM), a novel framework designed to enhance control in generative video composition and address its data scarcity problem. Unlike conventional methods relying on annotated datasets or handcrafted rules, StM…

Change detection (CD) in multitemporal remote sensing imagery presents significant challenges for fine-grained recognition, owing to heterogeneity and spatiotemporal misalignment. However, existing methodologies based on vision transformers…

Spatio-Temporal video grounding (STVG) focuses on retrieving the spatio-temporal tube of a specific object depicted by a free-form textual expression. Existing approaches mainly treat this complicated task as a parallel frame-grounding…

Bio-inspired Spiking Neural Networks (SNNs) provide an energy-efficient way to extract 3D spatio-temporal features. However, existing 3D SNNs have struggled with long-range dependencies until the recent emergence of Mamba, which offers…

Existing methods for instance segmentation in videos typically involve multi-stage pipelines that follow the tracking-by-detection paradigm and model a video clip as a sequence of images. Multiple networks are used to detect objects in…

Modelling various spatio-temporal dependencies is the key to recognising human actions in skeleton sequences. Most existing methods excessively relied on the design of traversal rules or graph topologies to draw the dependencies of the…

The rapid proliferation of surveillance cameras has increased the demand for automated violence detection. While CNNs and Transformers have shown success in extracting spatio-temporal features, they struggle with long-term dependencies and…

Despite remarkable advances in video generative models, they still struggle to generate physically realistic videos, frequently exhibiting appearance drift, implausible motion, and temporal inconsistencies. In this work, we address this…

3D Hand reconstruction from a single RGB image is challenging due to the articulated motion, self-occlusion, and interaction with objects. Existing SOTA methods employ attention-based transformers to learn the 3D hand pose and shape, yet…

Human trajectory forecasting is crucial for safe navigation in crowded environments, requiring models that balance accuracy with computational efficiency. Efficiently modeling social interactions is key to performance in dense crowds. Yet,…

While recent Transformer and Mamba architectures have advanced point cloud representation learning, they are typically developed for single-task or single-domain settings. Directly applying them to multi-task domain generalization (DG)…

We present Scene-Graph Based Multi-Modal Traffic Agent (SGTA), a modular framework for traffic video understanding that combines structured scene graphs with multi-modal reasoning. It constructs a traffic scene graph from roadside videos…

Next Point-of-Interest (POI) recommendation is a critical task in location-based services, yet it faces the fundamental challenge of coupled spatiotemporal asymmetry inherent in urban mobility. Specifically, transition intents between…