• Publications
  • Influence
Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification
TLDR
We show that it is possible to replace many of the 3D convolutions at the lowest layers of the network (the ones closest to the pixels), and use 2D convolution for the higher layers. Expand
  • 331
  • 83
  • PDF
DSENT - A Tool Connecting Emerging Photonics with Electronics for Opto-Electronic Networks-on-Chip Modeling
TLDR
We present DSENT, a NoC modeling tool for rapid design space exploration of electrical and opto-electrical networks. Expand
  • 446
  • 82
  • PDF
TALL: Temporal Activity Localization via Language Query
TLDR
We propose a novel Cross-modal Temporal Regression Localizer (CTRL) to jointly model text query and video clips, output alignment scores and action boundary regression results for candidate clips. Expand
  • 152
  • 61
  • PDF
TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals
TLDR
We propose a novel Temporal Unit Regression Network (TURN) model. Expand
  • 210
  • 35
  • PDF
Revisiting Unreasonable Effectiveness of Data in Deep Learning Era
TLDR
The success of deep learning in vision can be attributed to: (a) models with high capacity; (b) increased computational power; and (c) availability of large-scale labeled data. Expand
  • 635
  • 31
  • PDF
VideoBERT: A Joint Model for Video and Language Representation Learning
TLDR
In this paper, we propose a joint visual-linguistic model to learn high-level features without any explicit supervision. Expand
  • 191
  • 23
  • PDF
Rethinking Spatiotemporal Feature Learning For Video Understanding
TLDR
In this paper we study 3D convolutional networks for video understanding tasks. Expand
  • 115
  • 21
The iNaturalist Species Classification and Detection Dataset
TLDR
We present the iNaturalist species classification and detection dataset, consisting of 859,000 images from over 5,000 different species of plants and animals. Expand
  • 196
  • 19
  • PDF
NFP: Enabling Network Function Parallelism in NFV
TLDR
In this paper, we present NFP, a high performance framework, that innovatively enables network function parallelism to improve NFV performance. Expand
  • 104
  • 19
  • PDF
Beam Division Multiple Access Transmission for Massive MIMO Communications
TLDR
We study multicarrier multiuser multiple-input multiple-output (MU-MIMO) systems, in which the base station employs an asymptotically large number of antennas, and propose a beam division multiple access (BDMA) transmission scheme that simultaneously serves multiple users via different beams. Expand
  • 229
  • 18