Related papers: Masked Event Modeling: Self-Supervised Pretraining…

Labeling data (e.g., labeling the people, objects, actions and scene in images) comprehensively and efficiently is a widely needed but challenging task. Numerous models were proposed to label various data and many approaches were designed…

Event cameras are novel bio-inspired vision sensors that output pixel-level intensity changes in microsecond accuracy with a high dynamic range and low power consumption. Despite these advantages, event cameras cannot be directly applied to…

The success of deep learning in computer vision is rooted in the ability of deep networks to scale up model complexity as demanded by challenging visual tasks. As complexity is increased, so is the need for large amounts of labeled data to…

Emerging event cameras acquire visual information by detecting time domain brightness changes asynchronously at the pixel level and, unlike conventional cameras, are able to provide high temporal resolution, very high dynamic range, low…

Event-based vision sensors, inspired by biological neural systems, asynchronously capture local pixel-level intensity changes as a sparse event stream containing position, polarity, and timestamp information. These neuromorphic sensors…

Semi-supervised segmentation tackles the scarcity of annotations by leveraging unlabeled data with a small amount of labeled data. A prominent way to utilize the unlabeled data is by consistency training which commonly uses a…

Dense video captioning aims to generate corresponding text descriptions for a series of events in the untrimmed video, which can be divided into two sub-tasks, event detection and event captioning. Unlike previous works that tackle the two…

When a deep learning model is deployed in the wild, it can encounter test data drawn from distributions different from the training data distribution and suffer drop in performance. For safe deployment, it is essential to estimate the…

In recent years, event cameras have gained significant attention due to their bio-inspired properties, such as high temporal resolution and high dynamic range. However, obtaining large-scale labeled ground-truth data for event-based vision…

Recent advancements in event-based recognition have demonstrated significant promise, yet most existing approaches rely on extensive training, limiting their adaptability for efficient processing of event-driven visual content. Meanwhile,…

Self-supervised learning methods like masked autoencoders (MAE) have shown significant promise in learning robust feature representations, particularly in image reconstruction-based pretraining task. However, their performance is often…

Masked Image Modeling (MIM) has emerged as a promising method for deriving visual representations from unlabeled image data by predicting missing pixels from masked portions of images. It excels in region-aware learning and provides strong…

Observations with distributed sensors are essential in analyzing a series of human and machine activities (referred to as 'events' in this paper) in complex and extensive real-world environments. This is because the information obtained…

People segment complex, ever-changing and continuous experience into basic, stable and discrete spatio-temporal experience units, called events. Event segmentation literature investigates the mechanisms that allow people to extract events.…

Deep convolutional networks for semantic image segmentation typically require large-scale labeled data, e.g. ImageNet and MS COCO, for network pre-training. To reduce annotation efforts, self-supervised semantic segmentation is recently…

Masked Autoencoder (MAE) is a notable method for self-supervised pretraining in visual representation learning. It operates by randomly masking image patches and reconstructing these masked patches using the unmasked ones. A key limitation…

Learning transferable representations from unlabeled time series is crucial for improving performance in data-scarce classification. Existing self-supervised methods often operate at the point level and rely on unidirectional encoding,…

Facial expression plays an important role in understanding human emotions. Most recently, deep learning based methods have shown promising for facial expression recognition. However, the performance of the current state-of-the-art facial…

Event cameras offer low-power visual sensing capabilities ideal for edge-device applications. However, their high event rate, driven by high temporal details, can be restrictive in terms of bandwidth and computational resources. In edge AI…

Event cameras are novel sensors that output brightness changes in the form of a stream of asynchronous events instead of intensity frames. Compared to conventional image sensors, they offer significant advantages: high temporal resolution,…