Search Results for author: Ziheng Wang

Found 28 papers, 6 papers with code

Movie101v2: Improved Movie Narration Benchmark

1 code implementation20 Apr 2024 Zihao Yue, Yepeng Zhang, Ziheng Wang, Qin Jin

Automatic movie narration targets at creating video-aligned plot descriptions to assist visually impaired audiences.

Video Captioning

Weak Convergence Analysis of Online Neural Actor-Critic Algorithms

no code implementations25 Mar 2024 Samuel Chun-Hei Lam, Justin Sirignano, Ziheng Wang

Then, using a Poisson equation, we prove that the fluctuations of the model updates around the limit distribution due to the randomly-arriving data samples vanish as the number of parameter updates $\rightarrow \infty$.

An Efficient Sparse Inference Software Accelerator for Transformer-based Language Models on CPUs

1 code implementation28 Jun 2023 Haihao Shen, Hengyu Meng, Bo Dong, Zhe Wang, Ofir Zafrir, Yi Ding, Yu Luo, Hanwen Chang, Qun Gao, Ziheng Wang, Guy Boudoukh, Moshe Wasserblat

We apply our sparse accelerator on widely-used Transformer-based language models including Bert-Mini, DistilBERT, Bert-Base, and BERT-Large.

Model Compression

Concurrent Classifier Error Detection (CCED) in Large Scale Machine Learning Systems

no code implementations2 Jun 2023 Pedro Reviriego, Ziheng Wang, Alvaro Alonso, Zhen Gao, Farzad Niknia, Shanshan Liu, Fabrizio Lombardi

In this paper, we introduce Concurrent Classifier Error Detection (CCED), a scheme to implement CED in ML systems using a concurrent ML classifier to detect errors.

Image Classification

Movie101: A New Movie Understanding Benchmark

1 code implementation20 May 2023 Zihao Yue, Qi Zhang, Anwen Hu, Liang Zhang, Ziheng Wang, Qin Jin

Closer to real scenarios, the Movie Clip Narrating (MCN) task in our benchmark asks models to generate role-aware narration paragraphs for complete movie clips where no actors are speaking.

Video Captioning

Edit As You Wish: Video Description Editing with Multi-grained Commands

no code implementations15 May 2023 Linli Yao, Yuanmeng Zhang, Ziheng Wang, Xinglin Hou, Tiezheng Ge, Yuning Jiang, Qin Jin

In this paper, we propose a novel Video Description Editing (VDEdit) task to automatically revise an existing video description guided by flexible user requests.

Attribute Position +3

Uncertainty-aware Self-supervised Learning for Cross-domain Technical Skill Assessment in Robot-assisted Surgery

no code implementations28 Apr 2023 Ziheng Wang, Andrea Mariani, Arianna Menciassi, Elena De Momi, Ann Majewicz Fey

In this paper, we propose a novel approach for skill assessment by transferring domain knowledge from labeled kinematic data to unlabeled data.

Self-Supervised Learning

Automatic Detection of Out-of-body Frames in Surgical Videos for Privacy Protection Using Self-supervised Learning and Minimal Labels

no code implementations31 Mar 2023 Ziheng Wang, Conor Perreault, Xi Liu, Anthony Jarc

Endoscopic video recordings are widely used in minimally invasive robot-assisted surgery, but when the endoscope is outside the patient's body, it can capture irrelevant segments that may contain sensitive information.

Self-Supervised Learning

A Forward Propagation Algorithm for Online Optimization of Nonlinear Stochastic Differential Equations

no code implementations10 Jul 2022 Ziheng Wang, Justin Sirignano

We then re-write the algorithm using the PDE solution, which allows us to characterize the parameter evolution around the direction of steepest descent.

Continuous-time stochastic gradient descent for optimizing over the stationary distribution of stochastic differential equations

no code implementations14 Feb 2022 Ziheng Wang, Justin Sirignano

The gradient estimate is simultaneously updated using forward propagation of the SDE state derivatives, asymptotically converging to the direction of steepest descent.

SparseDNN: Fast Sparse Deep Learning Inference on CPUs

1 code implementation20 Jan 2021 Ziheng Wang

While we find mature support for quantized neural networks in production frameworks such as OpenVINO and MNN, support for pruned sparse neural networks is still lacking.


SparseRT: Accelerating Unstructured Sparsity on GPUs for Deep Learning Inference

no code implementations26 Aug 2020 Ziheng Wang

In recent years, there has been a flurry of research in deep neural network pruning and compression.

Network Pruning

Structured Pruning of Large Language Models

2 code implementations EMNLP 2020 Ziheng Wang, Jeremy Wohlwend, Tao Lei

Large language models have recently achieved state of the art performance across a wide variety of natural language tasks.

Language Modelling Model Compression +1

Accelerated CNN Training Through Gradient Approximation

no code implementations15 Aug 2019 Ziheng Wang, Sree Harsha Nelaturu

In this work, we explore three alternative methods to approximate gradients, with an efficient GPU kernel implementation for one of them.

Transferrable Operative Difficulty Assessment in Robot-assisted Teleoperation: A Domain Adaptation Approach

no code implementations12 Jun 2019 Ziheng Wang, Cong Feng, Jie Zhang, Ann Majewicz Fey

Providing an accurate and efficient assessment of operative difficulty is important for designing robot-assisted teleoperation interfaces that are easy and natural for human operators to use.

Steering Control Unsupervised Domain Adaptation

SATR-DL: Improving Surgical Skill Assessment and Task Recognition in Robot-assisted Surgery with Deep Neural Networks

no code implementations15 Jun 2018 Ziheng Wang, Ann Majewicz Fey

Purpose: This paper focuses on an automated analysis of surgical motion profiles for objective skill assessment and task recognition in robot-assisted surgery.

Representation Learning

A Hierarchical Probabilistic Model for Facial Feature Detection

no code implementations CVPR 2014 Yue Wu, Ziheng Wang, Qiang Ji

Facial feature detection from facial images has attracted great attention in the field of computer vision.

Structured Feature Selection

no code implementations ICCV 2015 Tian Gao, Ziheng Wang, Qiang Ji

Then we apply structured feature selection to two applications: 1) We introduce a new method that enables STMB to scale up and show the competitive performance of our algorithms on large-scale image classification tasks.

Dimensionality Reduction feature selection +2

Classifier Learning With Hidden Information

no code implementations CVPR 2015 Ziheng Wang, Qiang Ji

Experimental results on different applications demonstrate the effectiveness of the proposed methods for exploiting hidden information and their superior performance to existing methods.

Cannot find the paper you are looking for? You can Submit a new open access paper.