activity
20182020
most citedEagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning

13 citations · 27 across the 3 of their papers we have counts for

collaborators

5 papers

cs.CV20205 cited

Knowledge-Routed Visual Question Reasoning: Challenges for Deep Representation Embedding

Qingxing Cao, Bailin Li, Xiaodan Liang +2

Though beneficial for encouraging the Visual Question Answering (VQA) models to discover the underlying knowledge by exploiting the input-output correlation beyond image and text c…

cs.CV202013 cited

EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning

Bailin Li, Bowen Wu, Jiang Su +2

Finding out the computational redundant part of a trained Deep Neural Network (DNN) is the key question that pruning algorithms target on. Many algorithms try to predict model perf…

cs.CV20199 cited

Explainable High-order Visual Question Reasoning: A New Benchmark and Knowledge-routed Network

Qingxing Cao, Bailin Li, Xiaodan Liang +1

Explanation and high-order reasoning capabilities are crucial for real-world visual question answering with diverse levels of inference complexity (e.g., what is the dog that is ne…

cs.CV2018

Interpretable Visual Question Answering by Reasoning on Dependency Trees

Qingxing Cao, Bailin Li, Xiaodan Liang +1

Collaborative reasoning for understanding image-question pairs is a very critical but underexplored topic in interpretable visual question answering systems. Although very recent s…

cs.CV2018

Visual Question Reasoning on General Dependency Tree

Qingxing Cao, Xiaodan Liang, Bailing Li +2

The collaborative reasoning for understanding each image-question pair is very critical but under-explored for an interpretable Visual Question Answering (VQA) system. Although ver…