672 citations · 1.5k across the 24 of their papers we have counts for
7 papers · 1 filter
Localizing Moments in Video with Temporal Language
Lisa Anne Hendricks, Oliver Wang, Eli Shechtman +3
Localizing moments in a longer video via natural language queries is a new, challenging task at the intersection of language and video understanding. Though moment localization wit…
Object Hallucination in Image Captioning
Anna Rohrbach, Lisa Anne Hendricks, Kaylee Burns +2
Despite continuously improving performance, contemporary image captioning models are prone to "hallucinating" objects that are not actually in a scene. One problem is that standard…
Grounding Visual Explanations
Lisa Anne Hendricks, Ronghang Hu, Trevor Darrell +1
Existing visual explanation generating agents learn to fluently justify a class prediction. However, they may mention visual attributes which reflect a strong class prior, although…
Women also Snowboard: Overcoming Bias in Captioning Models (Extended Abstract)
Lisa Anne Hendricks, Kaylee Burns, Kate Saenko +2
Most machine learning methods are known to capture and exploit biases of the training data. While some biases are beneficial for learning, others are harmful. Specifically, image c…
Generating Counterfactual Explanations with Natural Language
Lisa Anne Hendricks, Ronghang Hu, Trevor Darrell +1
Natural language explanations of deep neural network decisions provide an intuitive way for a AI agent to articulate a reasoning process. Current textual explanations learn to disc…
Women also Snowboard: Overcoming Bias in Captioning Models
Kaylee Burns, Lisa Anne Hendricks, Kate Saenko +2
Most machine learning methods are known to capture and exploit biases of the training data. While some biases are beneficial for learning, others are harmful. Specifically, image c…
Multimodal Explanations: Justifying Decisions and Pointing to the Evidence
Dong Huk Park, Lisa Anne Hendricks, Zeynep Akata +4
Deep models that are both effective and explainable are desirable in many settings; prior explainable models have been unimodal, offering either image-based visualization of attent…