5 citations · 14 across the 12 of their papers we have counts for
6 papers · 1 filter
MotionDeltaCNN: Sparse CNN Inference of Frame Differences in Moving Camera Videos
Mathias Parger, Chengcheng Tang, Thomas Neff +4
Convolutional neural network inference on video input is computationally expensive and requires high memory bandwidth. Recently, DeltaCNN managed to reduce the cost by only process…
Arbitrary Bit-width Network: A Joint Layer-Wise Quantization and Adaptive Inference Approach
Chen Tang, Haoyu Zhai, Kai Ouyang +3
Conventional model quantization methods use a fixed quantization scheme to different data samples, which ignores the inherent "recognition difficulty" differences between various s…
Visual Pressure Estimation and Control for Soft Robotic Grippers
Patrick Grady, Jeremy A. Collins, Samarth Brahmbhatt +4
Soft robotic grippers facilitate contact-rich manipulation, including robust grasping of varied objects. Yet the beneficial compliance of a soft gripper also results in significant…
PressureVision: Estimating Hand Pressure from a Single RGB Image
Patrick Grady, Chengcheng Tang, Samarth Brahmbhatt +4
People often interact with their surroundings by applying pressure with their hands. While hand pressure can be measured by placing pressure sensors between the hand and the enviro…
Mixed-Precision Neural Network Quantization via Learned Layer-wise Importance
Chen Tang, Kai Ouyang, Zhi Wang +4
The exponentially large discrete search space in mixed-precision quantization (MPQ) makes it hard to determine the optimal bit-width for each layer. Previous works usually resort t…
DeltaCNN: End-to-End CNN Inference of Sparse Frame Differences in Videos
Mathias Parger, Chengcheng Tang, Christopher D. Twigg +3
Convolutional neural network inference on video data requires powerful hardware for real-time processing. Given the inherent coherence across consecutive frames, large parts of a v…