Related papers: It's About Time: Analog Clock Reading in the Wild
Previous works show that noisy, web-crawled image-text pairs may limit vision-language pretraining like CLIP and propose learning with synthetic captions as a promising alternative. Our work continues this effort, introducing two simple yet…
We present a method for synthesizing naturally looking images of multiple people interacting in a specific scenario. These images benefit from the advantages of synthetic data: being fully controllable and fully annotated with any type of…
Time series classification is a critical task in various domains, such as finance, healthcare, and sensor data analysis. Unsupervised contrastive learning has garnered significant interest in learning effective representations from time…
Beyond the existing single-person and multiple-person human parsing tasks in static images, this paper makes the first attempt to investigate a more realistic video instance-level human parsing that simultaneously segments out each person…
Sign Language Translation (SLT) aims to map sign language videos to spoken language text. A common approach relies on gloss annotations as an intermediate representation, decomposing SLT into two sub-tasks: video-to-gloss recognition and…
This document is focused on computing systems implemented in technologies that communicate and compute with temporal transients. Although described in general terms, implementations of spiking neural networks are of primary interest. As…
Post-silicon clock tuning elements are widely used in high-performance designs to mitigate the effects of process variations and aging. Located on clock paths to flip-flops, these tuning elements can be configured through the scan chain so…
Large-scale annotated datasets allow AI systems to learn from and build upon the knowledge of the crowd. Many crowdsourcing techniques have been developed for collecting image annotations. These techniques often implicitly rely on the fact…
Spiking neural networks (SNNs) equipped with latency coding and spike-timing dependent plasticity rules offer an alternative to solve the data and energy bottlenecks of standard computer vision approaches: they can learn visual features…
This paper focuses on self-supervised video representation learning. Most existing approaches follow the contrastive learning pipeline to construct positive and negative pairs by sampling different clips. However, this formulation tends to…
Temporal sampling does more than add another axis to the vector of observables. Instead, under the recognition that how objects change (and move) in time speaks directly to the physics underlying astronomical phenomena, next-generation…
Traditional human-in-the-loop-based annotation for time-series data like inertial data often requires access to alternate modalities like video or audio from the environment. These alternate sources provide the necessary information to the…
Learning-based methods for 3D scene reconstruction and object completion require large datasets containing partial scans paired with complete ground-truth geometry. However, acquiring such datasets using real-world scanning systems is…
When interacting with highly dynamic environments, scene flow allows autonomous systems to reason about the non-rigid motion of multiple independent objects. This is of particular interest in the field of autonomous driving, in which many…
Learning specific hands-on skills such as cooking, car maintenance, and home repairs increasingly happens via instructional videos. The user experience with such videos is known to be improved by meta-information such as time-stamped…
The ability of Generative Adversarial Networks to encode rich semantics within their latent space has been widely adopted for facial image editing. However, replicating their success with videos has proven challenging. Sets of high-quality…
This work focuses on the generation of a composite clock for time scales and shows the advantages of a more recent digital approach with respect to a traditional analog one. A digital approach directly processes the information contained…
Signal Temporal Logic (STL) is a convenient formalism to express bounded horizon properties of autonomous critical systems. STL extends LTL to real-valued signals and associates a non-singleton bound interval to each temporal operators. In…
Optical flow estimation is a crucial subfield of computer vision, serving as a foundation for video tasks. However, the real-world robustness is limited by animated synthetic datasets for training. This introduces domain gaps when applied…
Transformation optics has shaped up a revolutionary electromagnetic design paradigm, enabling scientists to build astonishing devices such as invisibility cloaks. Unfortunately, the application of transformation techniques to other branches…