相关论文: MOOSS: Mask-Enhanced Temporal Contrastive Learning…

Multi-mode tensor time series (TTS) can be found in many domains, such as search engines and environmental monitoring systems. Learning representations of a TTS benefits various applications, but it is also challenging since the…

Contrastive learning has become pivotal in unsupervised representation learning, with frameworks like Momentum Contrast (MoCo) effectively utilizing large negative sample sets to extract discriminative features. However, traditional…

For deep reinforcement learning (RL) from pixels, learning effective state representations is crucial for achieving high performance. However, in practice, limited experience and high-dimensional inputs prevent effective representation…

Meta-reinforcement learning enables artificial agents to learn from related training tasks and adapt to new tasks efficiently with minimal interaction data. However, most existing research is still limited to narrow task distributions that…

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…

Improving sample efficiency is a key research problem in reinforcement learning (RL), and CURL, which uses contrastive learning to extract high-level features from raw pixels of individual video frames, is an efficient…

Large-scale single-stream pre-training has shown dramatic performance in image-text retrieval. Regrettably, it faces low inference efficiency due to heavy attention layers. Recently, two-stream methods like CLIP and ALIGN with high…

Contrastive learning, as a self-supervised learning paradigm, becomes popular for Multivariate Time-Series (MTS) classification. It ensures the consistency across different views of unlabeled samples and then learns effective…

We introduce MOSAIC (Masked Objective with Selective Adaptation for In-domain Contrastive learning), a multi-stage framework for domain adaptation of text embedding models that incorporates joint domain-specific masked supervision. Our…

A prevailing approach for learning visuomotor policies is to employ reinforcement learning to map high-dimensional visual observations directly to action commands. However, the combination of high-dimensional visual inputs and agile…

Contrastive self-supervised learning has outperformed supervised pretraining on many downstream tasks like segmentation and object detection. However, current methods are still primarily applied to curated datasets like ImageNet. In this…

Learning dynamics is essential for model-based control and Reinforcement Learning in engineering systems, such as robotics and power systems. However, limited system measurements, such as those from low-resolution sensors, demand…

Modality representation learning is an important problem for multimodal sentiment analysis (MSA), since the highly distinguishable representations can contribute to improving the analysis effect. Previous works of MSA have usually focused…

Learning-based multi-view stereo (MVS) methods have made impressive progress and surpassed traditional methods in recent years. However, their accuracy and completeness are still struggling. In this paper, we propose a new method to enhance…

MoCo is effective for unsupervised image representation learning. In this paper, we propose VideoMoCo for unsupervised video representation learning. Given a video sequence as an input sample, we improve the temporal feature representations…

Multi-modality spatio-temporal (MoST) data extends spatio-temporal (ST) data by incorporating multiple modalities, which is prevalent in monitoring systems, encompassing diverse traffic demands and air quality assessments. Despite…

To equip artificial intelligence with a comprehensive understanding towards a temporal world, video and 4D panoptic scene graph generation abstracts visual data into nodes to represent entities and edges to capture temporal relations.…

Masked video modeling~(MVM) has emerged as a highly effective pre-training strategy for visual foundation models, whereby the model reconstructs masked spatiotemporal tokens using information from visible tokens. However, a key challenge in…

Despite recent progress in reinforcement learning (RL) from raw pixel data, sample inefficiency continues to present a substantial obstacle. Prior works have attempted to address this challenge by creating self-supervised auxiliary tasks,…

Advanced self-supervised visual representation learning methods rely on the instance discrimination (ID) pretext task. We point out that the ID task has an implicit semantic consistency (SC) assumption, which may not hold in unconstrained…