相关论文: Mode-as-Sequence: Translating Multimodal Motion Pr…

Accurately anticipating how complex, diverse scenes will evolve requires models that represent uncertainty, simulate along extended interaction chains, and efficiently explore many plausible futures. Yet most existing approaches rely on…

How to learn discriminative video representation from unlabeled videos is challenging but crucial for video analysis. The latest attempts seek to learn a representation model by predicting the appearance contents in the masked regions.…

Parallel sampling promises substantial gains in test-time scaling, but its effectiveness is sharply limited by diversity collapse, where models concentrate on a few modes and repeated samples produce the same mistakes. We propose the…

Traditional language models, adept at next-token prediction in text sequences, often struggle with transduction tasks between distinct symbolic systems, particularly when parallel data is scarce. Addressing this issue, we introduce…

Many vision-related tasks benefit from reasoning over multiple modalities to leverage complementary views of data in an attempt to learn robust embedding spaces. Most deep learning-based methods rely on a late fusion technique whereby…

Self-supervised learning is an efficient pre-training method for medical image analysis. However, current research is mostly confined to specific-modality data pre-training, consuming considerable time and resources without achieving…

Recent works in multiple object tracking use sequence model to calculate the similarity score between the detections and the previous tracklets. However, the forced exposure to ground-truth in the training stage leads to the…

Self-supervised feature learning enables perception systems to benefit from the vast raw data recorded by vehicle fleets worldwide. While video-level self-supervised learning approaches have shown strong generalizability on classification…

In this work, we investigate unsupervised representation learning on medical time series, which bears the promise of leveraging copious amounts of existing unlabeled data in order to eventually assist clinical decision making. By evaluating…

Recent advances in remote health monitoring systems have significantly benefited patients and played a crucial role in improving their quality of life. However, while physiological health-focused solutions have demonstrated increasing…

Human motion prediction is a classical problem in computer vision and computer graphics, which has a wide range of practical applications. Previous effects achieve great empirical performance based on an encoding-decoding style. The methods…

Multivariate time series forecasting plays a crucial role in various real-world applications. Significant efforts have been made to integrate advanced network architectures and training strategies that enhance the capture of temporal…

In this work, we pursue a unified paradigm for multimodal pretraining to break the scaffolds of complex task/modality-specific customization. We propose OFA, a Task-Agnostic and Modality-Agnostic framework that supports Task…

As large-scale time-series data can easily be found in real-world applications, multivariate time-series anomaly detection has played an essential role in diverse industries. It enables productivity improvement and maintenance cost…

Unsupervised learning has been popular in various computer vision tasks, including visual object tracking. However, prior unsupervised tracking approaches rely heavily on spatial supervision from template-search pairs and are still unable…

Predicting high-fidelity future human poses, from a historically observed sequence, is decisive for intelligent robots to interact with humans. Deep end-to-end learning approaches, which typically train a generic pre-trained model on…

Pre-trained segmentation models are a powerful and flexible tool for segmenting images. Recently, this trend has extended to medical imaging. Yet, often these methods only produce a single prediction for a given image, neglecting inherent…

Autonomous Vehicle decisions rely on multimodal prediction models that account for multiple route options and the inherent uncertainty in human behavior. However, models can suffer from mode collapse, where only the most likely mode is…

Motion simulation, prediction and planning are foundational tasks in autonomous driving, each essential for modeling and reasoning about dynamic traffic scenarios. While often addressed in isolation due to their differing objectives, such…

Autoregressive models (ARMs) are hindered by slow sequential inference. While masked diffusion models (MDMs) offer a parallel alternative, they suffer from critical drawbacks: high computational overhead from precluding Key-Value (KV)…