◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Peng Xu

24 papers hereh-index 161.1k citations26 works total

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • first author6
  • middle author17
  • last author1

Across the 24 of 24 papers where every author was matched, so the position is known.

fields
  • cs.CL13
  • cs.CV7
  • cs.IR2
  • cs.LG2
same name
  • Peng Xu — 23 papers, h 20
  • Peng Xu — 20 papers, h 17
  • Peng Xu — 18 papers, h 17
  • Peng Xu — 18 papers, h 4
  • Peng Xu — 17 papers, h 9
  • Peng Xu — 13 papers, h 9

Either other researchers who publish under this name, or the same person where the external sources have not merged their records.

identity via Semantic Scholar / OpenAlex

activity
20182023
most citedSAM Struggles in Concealed Scenes -- Empirical Study on Segment Anything

97 citations · 350 across the 22 of their papers we have counts for

collaborators
Showing 2019Show all

4 papers · 1 filter

cs.CV2019★ 5 cited

SPIN: A High Speed, High Resolution Vision Dataset for Tracking and Action Recognition in Ping Pong

Steven Schwarcz, Peng Xu, David D'Ambrosio +4

We introduce a new high resolution, high frame rate stereo video dataset, which we call SPIN, for tracking and action recognition in the game of ping pong. The corpus consists of p…

cs.CV2019

Boosting Image Recognition with Non-differentiable Constraints

Xuan Li, Yuchen Lu, Peng Xu +3

In this paper, we study the problem of image recognition with non-differentiable constraints. A lot of real-life recognition applications require a rich output structure with deter…

cs.CL2019★ 24 cited

CAiRE: An Empathetic Neural Chatbot

Zhaojiang Lin, Peng Xu, Genta Indra Winata +4

In this paper, we present an end-to-end empathetic conversation agent CAiRE. Our system adapts TransferTransfo (Wolf et al., 2019) learning approach that fine-tunes a large-scale p…

cs.IR2019★ 16 cited

Passage Ranking with Weak Supervision

Peng Xu, Xiaofei Ma, Ramesh Nallapati +1

In this paper, we propose a \textit{weak supervision} framework for neural ranking tasks based on the data programming paradigm \citep{Ratner2016}, which enables us to leverage mul…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.