activity
20152019
most citedTowards Good Practices for Very Deep Two-Stream ConvNets

385 citations · 884 across the 10 of their papers we have counts for

collaborators

13 papers

cs.IR20196 cited

Dynamically Visual Disambiguation of Keyword-based Image Search

Yazhou Yao, Zeren Sun, Fumin Shen +6

Due to the high cost of manual annotation, learning directly from the web has attracted broad attention. One issue that limits their performance is the problem of visual polysemy.…

cs.CV20193 cited

Translate-to-Recognize Networks for RGB-D Scene Recognition

Dapeng Du, Limin Wang, Huiling Wang +2

Cross-modal transfer is helpful to enhance modality-specific discriminative power for scene recognition. To this end, this paper presents a unified framework to integrate the tasks…

cs.CV20191 cited

Learning Actor Relation Graphs for Group Activity Recognition

Jianchao Wu, Limin Wang, Li Wang +2

Modeling relation between actors is important for recognizing group activity in a multi-person scene. This paper aims at learning discriminative relation between actors efficiently…

cs.CV201810 cited

Structured Triplet Learning with POS-tag Guided Attention for Visual Question Answering

Zhe Wang, Xiaoyi Liu, Liangjian Chen +4

Visual question answering (VQA) is of significant interest due to its potential to be a strong test of image understanding systems and to probe the connection between language and…

cs.CV2017313 cited

WebVision Database: Visual Learning and Understanding from Web Data

Wen Li, Limin Wang, Wei Li +2

In this paper, we present a study on learning visual recognition models from large scale noisy web data. We build a new database called WebVision, which contains more than mi…

cs.CV201714 cited

WebVision Challenge: Visual Learning and Understanding With Web Data

Wen Li, Limin Wang, Wei Li +5

We present the 2017 WebVision Challenge, a public image recognition challenge designed for deep learning based on web images without instance-level human annotation. Following the…