-
DCC 20232023Motion Compensated Temporal Filtering (MCTF) is a pre-processing approach employed prior to video encoding, for improving the compression efficiency. Prior MCTF designs (e.g. [1]) use pre-defined frame-level quantization parameters (QPs) for different slice types and temporal layers, and operate with a fixed Group of Pictures (GOP) structure. However, commercial encoders can adapt GOP structure based upon
-
2023We propose an approach to estimate the number of samples required for a model to reach a target performance. We find that the power law, the de facto principle to estimate model performance, leads to large error when using a small dataset (e.g., 5 samples per class) for extrapolation. This is because the log-performance error against the log-dataset size follows a nonlinear progression in the few-shot regime
-
2023Humans naturally decompose their environment into entities at the appropriate level of abstraction to act in the world. Allowing machine learning algorithms to derive this decomposition in an unsupervised way has become an important line of research. However, current methods are restricted to simulated data or require additional information in the form of motion or depth in order to successfully discover
-
High Dynamic Range (HDR) video streaming has become more popular because of the faithful color and brightness presentation. However, the live streaming of HDR, especially of sports content, has unique challenges, as it was usually encoded and distributed in real-time without the post-production workflow. A set of unique problems that occurs only in live streaming, e.g. resolution and frame rate crossover
-
2023Recent vision transformer based video models mostly follow the “image pretraining then finetuning” paradigm and have achieved great success on multiple video benchmarks. However, full finetuning such a video model could be computationally expensive and unnecessary, given the pre-trained image transformer models have demonstrated exceptional transferability. In this work, we propose a novel method to Adapt
Related content
-
February 14, 2023A diversity of outputs ensures that style transfer model can satisfy any user’s tastes.
-
January 05, 2023How an AWS customer uses Lookout for Vision to build custom computer vision models to automate quality inspection and detect defects.
-
January 04, 2023As video scales up — in both duration and resolution — it raises new research questions.
-
January 03, 2023Automated methods with a little human guidance use annotators’ time much more efficiently.
-
December 26, 2022Combining contrastive training and selection of hard negative examples establishes new benchmarks.
-
December 16, 2022University of Wisconsin-Madison associate professor and ARA recipient has authored a series of pioneering papers on real-time object instance segmentation.
-
December 09, 2022Why multimodal identification is a crucial step in automating item identification at Amazon scale.
-
November 22, 2022Francesco Locatello on the four NeurIPS papers he coauthored this year, which largely concern generalization to out-of-distribution test data.
-
November 15, 2022Models that map spoken language to objects in an image would make it easier for customers to communicate with multimodal devices.
-
November 10, 2022New approach can cut the setup time required to develop vision-based machine learning solutions from between six to twelve months to one or two.
-
November 08, 2022Eliminating the need for annotation makes bias testing much more practical.
-
November 01, 2022By plotting nonlinear trajectories through a GAN’s latent space, the method enables certain image attributes to vary while others are held fixed.
-
October 27, 2022A model that estimates depth from 2-D images learns to adjust to differences between images produced by different cameras, reducing error by about 20%.
-
October 26, 2022Research topics range from visual anomaly detection to road network extraction, regression-constrained neural-architecture search to self-supervised learning for video representations.
-
October 24, 2022Company is testing a new class of robots that use artificial intelligence and computer vision to move freely throughout facilities.
-
October 05, 2022Inaugural recipients named as part of the JHU + Amazon Initiative for Interactive AI (AI2AI).
-
September 19, 2022Why detecting damage is so tricky at Amazon’s scale — and how researchers are training robots to help with that gargantuan task.
-
August 16, 2022ARA recipient is using artificial intelligence to help doctors make decisions based on radiological data.
-
July 20, 2022Violetta Shevchenko, an Amazon applied scientist and former intern, combines vision and language to create solutions to challenging problems.
-
July 01, 2022Two methods presented at CVPR achieve state-of-the-art results by imposing additional structure on the representational space.
-
June 24, 2022Technique that mixes public and private training data can meet differential-privacy criteria while cutting error increase by 60%-70%.