Picture for Menglong Zhu

Menglong Zhu

DJI Innovations Inc

Binary Neural Networks as a general-propose compute paradigm for on-device computer vision

Add code
Feb 08, 2022
Figure 1 for Binary Neural Networks as a general-propose compute paradigm for on-device computer vision
Figure 2 for Binary Neural Networks as a general-propose compute paradigm for on-device computer vision
Figure 3 for Binary Neural Networks as a general-propose compute paradigm for on-device computer vision
Figure 4 for Binary Neural Networks as a general-propose compute paradigm for on-device computer vision
Viaarxiv icon

SpotPatch: Parameter-Efficient Transfer Learning for Mobile Object Detection

Jan 04, 2021
Figure 1 for SpotPatch: Parameter-Efficient Transfer Learning for Mobile Object Detection
Figure 2 for SpotPatch: Parameter-Efficient Transfer Learning for Mobile Object Detection
Figure 3 for SpotPatch: Parameter-Efficient Transfer Learning for Mobile Object Detection
Figure 4 for SpotPatch: Parameter-Efficient Transfer Learning for Mobile Object Detection
Viaarxiv icon

Rethinking RGB-D Salient Object Detection: Models, Datasets, and Large-Scale Benchmarks

Add code
Jul 15, 2019
Figure 1 for Rethinking RGB-D Salient Object Detection: Models, Datasets, and Large-Scale Benchmarks
Figure 2 for Rethinking RGB-D Salient Object Detection: Models, Datasets, and Large-Scale Benchmarks
Figure 3 for Rethinking RGB-D Salient Object Detection: Models, Datasets, and Large-Scale Benchmarks
Figure 4 for Rethinking RGB-D Salient Object Detection: Models, Datasets, and Large-Scale Benchmarks
Viaarxiv icon

Looking Fast and Slow: Memory-Guided Mobile Video Object Detection

Add code
Mar 25, 2019
Figure 1 for Looking Fast and Slow: Memory-Guided Mobile Video Object Detection
Figure 2 for Looking Fast and Slow: Memory-Guided Mobile Video Object Detection
Figure 3 for Looking Fast and Slow: Memory-Guided Mobile Video Object Detection
Figure 4 for Looking Fast and Slow: Memory-Guided Mobile Video Object Detection
Viaarxiv icon

Detect-to-Retrieve: Efficient Regional Aggregation for Image Search

Add code
Dec 04, 2018
Figure 1 for Detect-to-Retrieve: Efficient Regional Aggregation for Image Search
Figure 2 for Detect-to-Retrieve: Efficient Regional Aggregation for Image Search
Figure 3 for Detect-to-Retrieve: Efficient Regional Aggregation for Image Search
Figure 4 for Detect-to-Retrieve: Efficient Regional Aggregation for Image Search
Viaarxiv icon

MobileNetV2: Inverted Residuals and Linear Bottlenecks

Add code
Apr 02, 2018
Figure 1 for MobileNetV2: Inverted Residuals and Linear Bottlenecks
Figure 2 for MobileNetV2: Inverted Residuals and Linear Bottlenecks
Figure 3 for MobileNetV2: Inverted Residuals and Linear Bottlenecks
Figure 4 for MobileNetV2: Inverted Residuals and Linear Bottlenecks
Viaarxiv icon

Mobile Video Object Detection with Temporally-Aware Feature Maps

Add code
Mar 28, 2018
Figure 1 for Mobile Video Object Detection with Temporally-Aware Feature Maps
Figure 2 for Mobile Video Object Detection with Temporally-Aware Feature Maps
Figure 3 for Mobile Video Object Detection with Temporally-Aware Feature Maps
Figure 4 for Mobile Video Object Detection with Temporally-Aware Feature Maps
Viaarxiv icon

MonoCap: Monocular Human Motion Capture using a CNN Coupled with a Geometric Prior

Add code
Mar 09, 2018
Figure 1 for MonoCap: Monocular Human Motion Capture using a CNN Coupled with a Geometric Prior
Figure 2 for MonoCap: Monocular Human Motion Capture using a CNN Coupled with a Geometric Prior
Figure 3 for MonoCap: Monocular Human Motion Capture using a CNN Coupled with a Geometric Prior
Figure 4 for MonoCap: Monocular Human Motion Capture using a CNN Coupled with a Geometric Prior
Viaarxiv icon

Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference

Add code
Dec 15, 2017
Figure 1 for Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference
Figure 2 for Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference
Figure 3 for Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference
Figure 4 for Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference
Viaarxiv icon

Automatic Spatially-aware Fashion Concept Discovery

Aug 03, 2017
Figure 1 for Automatic Spatially-aware Fashion Concept Discovery
Figure 2 for Automatic Spatially-aware Fashion Concept Discovery
Figure 3 for Automatic Spatially-aware Fashion Concept Discovery
Figure 4 for Automatic Spatially-aware Fashion Concept Discovery
Viaarxiv icon