-
2023This paper addresses the challenge of reconstructing a scene with a neural radiance field (NeRF) for robot vision and scene understanding using multiple modalities. Researchers have introduced the use of NeRF to represent an object for synthesizing and rendering novel views of complex scenes by optimizing a 3-D radiance field for ray casting and rendering for 2-D RGB images. However, using RGB images alone
-
2023Rotated bounding boxes drastically reduce output ambiguity of elongated objects, making it superior to axis-aligned bounding boxes. Despite the effectiveness, rotated detectors are not widely employed. Annotating rotated bounding boxes is such a laborious process that they are not provided in many detection datasets where axis-aligned annotations are used instead. In this paper, we propose a framework that
-
2023This paper introduces Amazon Robotic Manipulation Benchmark (ARMBench), a large-scale, object-centric benchmark dataset for robotic manipulation in the context of a warehouse. Automation of operations in modern warehouses requires a robotic manipulator to deal with a wide variety of objects, unstructured storage, and dynamically changing inventory. Such settings pose challenges in perceiving the identity
-
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
Related content
-
June 24, 2022The field motivated him to pursue a PhD, which eventually led him to Amazon.
-
June 23, 2022EMVA Young Professional Award honors “outstanding and innovative work of a student or a young professional in the field of machine vision or image processing.”
-
June 22, 2022CVPR papers examine the recovery of 3-D information from camera movement and learning general representations from weakly annotated data.
-
June 21, 2022How she moved across the world to discover a passion for (and a career in) machine learning.
-
June 20, 2022Amazon’s director of applied science in Adelaide, Australia, believes the economic value of computer vision has “gone through the roof".
-
June 16, 2022Senior principal scientist Aleix M. Martinez on why computer vision research has only begun to scratch the surface.
-
June 02, 2022The Amazon Scholar received the award for his seminal and sustained contributions to the fields of computer graphics and visual computing.
-
May 27, 2022The first Amazon Science Hub to exist outside the US will focus on driving AI research and development throughout Germany.
-
May 26, 2022Reformulating the mapping problem to take advantage of sequence-to-sequence Transformers improves performance by an average of 15%.
-
May 03, 2022How a math-loving student travelled 7,000 miles to pursue a passion and wound up becoming an applied scientist.
-
April 19, 2022Deep learning to produce invariant representations, estimations of sensor reliability, and efficient map representations all contribute to Astro’s superior spatial intelligence.
-
April 18, 2022An advanced perception system, which detects and learns from its own mistakes, enables Robin robots to select individual objects from jumbled packages — at production scale.
-
March 04, 2022Detectors for block corruption, audio artifacts, and errors in audio-video synchronization are just three of Prime Video’s quality assurance tools.
-
February 02, 2022The Amazon Scholar and Johns Hopkins University professor was honored for “pioneering contributions to subspace clustering”.
-
January 14, 2022A new metric-learning loss function groups together superclasses and learns commonalities within them.
-
January 10, 2022Method uses metric learning to determine whether images depict the same product.
-
January 06, 2022Amazon’s Joe Tighe on the major trends he sees in the field of computer vision.
-
January 04, 2022A combination of deep learning, natural language processing, and computer vision enables Amazon to hone in on the right amount of packaging for each product.
-
December 07, 2021Synthetic data produced by perturbing test inputs identify error classes and provide additional data for retraining.
-
November 18, 2021In Conversation Mode, Alexa detects device-directed speech without the need for the wake word.
-
November 03, 2021Amazon Research Award recipient Yezhou Yang is studying how to make autonomous systems more robust.