相关论文: MoBind: Motion Binding for Fine-Grained IMU-Video …

Monocular 3D motion capture (mocap) is beneficial to many applications. The use of a single camera, however, often fails to handle occlusions of different body parts and hence it is limited to capture relatively simple movements. We present…

In the field of 3D object detection tasks, fusing heterogeneous features from LiDAR and camera sensors into a unified Bird's Eye View (BEV) representation is a widely adopted paradigm. However, existing methods often suffer from imprecise…

Unified multi-model representation spaces are the foundation of multimodal understanding and generation. However, the billions of model parameters and catastrophic forgetting problems make it challenging to further enhance pre-trained…

Large language models with instruction-following abilities have revolutionized the field of artificial intelligence. These models show exceptional generalizability to tackle various real-world tasks through their natural language…

Predicting a ligand's bound pose to a target protein is a key component of early-stage computational drug discovery. Recent developments in machine learning methods have focused on improving pose quality at the cost of model runtime. For…

Fine-grained image-text alignment is a pivotal challenge in multimodal learning, underpinning key applications such as visual question answering, image captioning, and vision-language navigation. Unlike global alignment, fine-grained…

The video-language (VL) pretraining has achieved remarkable improvement in multiple downstream tasks. However, the current VL pretraining framework is hard to extend to multiple modalities (N modalities, N>=3) beyond vision and language. We…

Learning effective motion features is an essential pursuit of video representation learning. This paper presents a simple yet effective sample construction strategy to boost the learning of motion features in video contrastive learning. The…

By learning human motion priors, motion capture can be achieved by 6 inertial measurement units (IMUs) in recent years with the development of deep learning techniques, even though the sensor inputs are sparse and noisy. However, human…

Advances in machine learning and wearable sensors offer new opportunities for capturing and analyzing human movement outside specialized laboratories. Accurate assessment of human movement under real-world conditions is essential for…

Masked image modeling (MIM) with transformer backbones has recently been exploited as a powerful self-supervised pre-training technique. The existing MIM methods adopt the strategy to mask random patches of the image and reconstruct the…

Cluttered bin-picking environments are challenging for pose estimation models. Despite the impressive progress enabled by deep learning, single-view RGB pose estimation models perform poorly in cluttered dynamic environments. Imbuing the…

Wearable sensors such as Inertial Measurement Units (IMUs) are often used to assess the performance of human exercise. Common approaches use handcrafted features based on domain expertise or automatically extracted features using time…

One central question for video action recognition is how to model motion. In this paper, we present hierarchical contrastive motion learning, a new self-supervised learning framework to extract effective motion representations from raw…

Multimodal sensing systems are increasingly prevalent in various real-world applications. Most existing multimodal learning approaches heavily rely on training with a large amount of synchronized, complete multimodal data. However, such a…

IMUs are regularly used to sense human motion, recognize activities, and estimate full-body pose. Users are typically required to place sensors in predefined locations that are often dictated by common wearable form factors and the machine…

Cross-modal alignment aims to map heterogeneous modalities into a shared latent space, as exemplified by models like CLIP, which benefit from large-scale image-text pretraining for strong recognition capabilities. However, when operating in…

Despite recent progress in Multi-Modal Large Language Models (MLLMs), it remains challenging to integrate diverse tasks ranging from pixel-level perception to high-fidelity generation. Existing approaches often suffer from either restricted…

We propose to estimate 3D human pose from multi-view images and a few IMUs attached at person's limbs. It operates by firstly detecting 2D poses from the two signals, and then lifting them to the 3D space. We present a geometric approach to…

We present MultiBodySync, a novel, end-to-end trainable multi-body motion segmentation and rigid registration framework for multiple input 3D point clouds. The two non-trivial challenges posed by this multi-scan multibody setting that we…