• Publications
  • Influence
Temporal Segment Networks: Towards Good Practices for Deep Action Recognition
Deep convolutional networks have achieved great success for visual recognition in still images. However, for action recognition in videos, the advantage over traditional methods is not so evident.Expand
  • 1,406
  • 334
Multi-Probe LSH: Efficient Indexing for High-Dimensional Similarity Search
Similarity indices for high-dimensional data are very desirable for building content-based search systems for feature-rich data such as audio, images, videos, and other sensor data. Recently,Expand
  • 713
  • 111
Towards Good Practices for Very Deep Two-Stream ConvNets
Deep convolutional networks have achieved great success for object recognition in still images. However, for action recognition in videos, the improvement of deep convolutional networks is not soExpand
  • 291
  • 61
APD2: the updated antimicrobial peptide database and its application in peptide design
The antimicrobial peptide database (APD, http://aps.unmc.edu/AP/main.php) has been updated and expanded. It now hosts 1228 entries with 65 anticancer, 76 antiviral (53 anti-HIV), 327 antifungal andExpand
  • 772
  • 56
HermiT: An OWL 2 Reasoner
This system description paper introduces the OWL 2 reasoner HermiT. The reasoner is fully compliant with the OWL 2 Direct Semantics as standardised by the World Wide Web Consortium (W3C). HermiT isExpand
  • 334
  • 46
APD: the Antimicrobial Peptide Database
An antimicrobial peptide database (APD) has been established based on an extensive literature search. It contains detailed information for 525 peptides (498 antibacterial, 155 antifungal, 28Expand
  • 605
  • 41
APD3: the antimicrobial peptide database as a tool for research and education
The antimicrobial peptide database (APD, http://aps.unmc.edu/AP/) is an original database initially online in 2003. The APD2 (2009 version) has been regularly updated and further expanded into theExpand
  • 533
  • 40
Efficient top-K query calculation in distributed networks
This paper presents a new algorithm to answer top-k queries (e.g. "find the k objects with the highest aggregate values") in a distributed network. Existing algorithms such as the Threshold AlgorithmExpand
  • 283
  • 35
Detection of LSB Steganography via Sample Pair Analysis
This paper introduces a new, principled approach to detecting LSB steganography in digital signals such as images and audio. It is shown that the length of hidden message embedded in the leastExpand
  • 277
  • 33
Temporal Segment Networks for Action Recognition in Videos
We present a general and flexible video-level framework for learning action models in videos. This method, called temporal segment network (TSN), aims to model long-range temporal structure with aExpand
  • 116
  • 30