2024


  • Incorporating Geo-Diverse Knowledge into Prompting for Increased Geographical Robustness in Object Recognition. Kyle Buettner, Sina Malakouti, Xiang Lorraine Li, Adriana Kovashka. To appear, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2024.

  • Synonym relations affect object detection learned on vision-language data. Giacomo Nebbia and Adriana Kovashka. To appear, North American Chapter of the Association for Computational Linguistics (NAACL) Findings, June 2024.

  • VEIL: Vetting Extracted Image Labels from In-the-Wild Captions for Weakly-Supervised Object Detection. Arushi Rai and Adriana Kovashka. To appear, European Chapter of the Association for Computational Linguistics (EACL), March 2024.

  • Investigating the Role of Attribute Context in Vision-Language Models for Object Recognition and Detection. Kyle Buettner and Adriana Kovashka. In Winter Conference on Applications of Computer Vision (WACV), January 2024. [pdf]

  • Boosting Weakly Supervised Object Detection using Fusion and Priors from Hallucinated Depth. Cagri Gungor and Adriana Kovashka. In Winter Conference on Applications of Computer Vision (WACV), January 2024. [pdf]
  • 2023


  • Semi-Supervised Domain Generalization for Object Detection via Language-Guided Feature Alignment. Sina Malakouti and Adriana Kovashka. To appear, British Machine Vision Conference (BMVC), November 2023. [pdf]

  • Decoding Symbolism in Language Models. Meiqi Guo, Rebecca Hwa and Adriana Kovashka. To appear, Annual Meeting of the Association for Computational Linguistics (ACL), July 2023. [pdf]

  • Hypernymization of Named Entity-rich captions for grounding-based multi-modal pretraining. Giacomo Nebbia and Adriana Kovashka. In ACM International Conference on Multimedia Retrieval (ICMR), June 2023. [pdf]

  • Towards Shape-regularized Learning for Mitigating Texture Bias in CNNs. Harsh Sinha and Adriana Kovashka. In ACM International Conference on Multimedia Retrieval (ICMR), June 2023. [pdf]

  • Complementary Cues from Audio Help Combat Noise in Weakly-Supervised Object Detection. Cagri Gungor and Adriana Kovashka. In Winter Conference on Applications of Computer Vision (WACV), January 2023. [pdf]

  • How to Practice VQA on a Resource-limited Target Domain. Mingda Zhang, Rebecca Hwa, Adriana Kovashka. In Winter Conference on Applications of Computer Vision (WACV), January 2023. [pdf]

  • Is misrecognition by teachable agents bad for students? Yuya Asano, Diane Litman, Mingzhi Yu, Nikki Lobczowski, Timothy Nokes-Malach, Adriana Kovashka and Erin Walker. To appear, International Conference on Artificial Intelligence in Education (AIED), July 2023. Poster. [pdf]

  • Contrastive View Design Strategies to Enhance Robustness to Domain Shifts in Downstream Object Detection. Kyle Buettner and Adriana Kovashka. In AAAI Workshop on Practical Deep Learning in the Wild (AAAIW Practical-DL), February 2023. [pdf]

  • Improving language-supervised object detection with linguistic structure analysis. Arushi Rai and Adriana Kovashka. To appear, Workshop on Open-Domain Reasoning Under Multi-Modal Settings (O-DRUM), held in conjunction with the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2023. [pdf]
  • 2022


  • Learning to Overcome Noise in Weak Caption Supervision for Object Detection. Mesut Erhan Unal, Keren Ye, Mingda Zhang, Christopher Thomas, Adriana Kovashka, Wei Li, Danfeng Qin, Jesse Berent. In Transactions of Pattern Analysis and Machine Intelligence (TPAMI), 2022. [pdf]

  • Building a Reinforcement Learning Environment from Limited Data to Optimize Teachable Robot Interventions. Tristan Maidment, Mingzhi Yu, Nikki Lobczowski, Adriana Kovashka, Erin Walker, Diane Litman and Timothy Nokes-Malach. In The 15th International Conference on Educational Data Mining (EDM), July 2022. [pdf]

  • Comparison of Lexical Alignment with a Teachable Robot in Human-Robot and Human-Human-Robot Interactions. Yuya Asano, Diane Litman, Mingzhi Yu, Nikki Lobczowski, Timothy Nokes-Malach, Adriana Kovashka, Erin Walker. In Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL), September 2022. [pdf]

  • Characterizing User Susceptibility to COVID-19 Misinformation on Twitter. Xian Teng, Yu-Ru Lin, Wen-Ting Chung, Ang Li and Adriana Kovashka. In International AAAI Conference on Web and Social Media (ICWSM), June 2022. [pdf]

  • The Role of Shape for Domain Generalization on Sparsely-Textured Images. Narges Honarvar Nazari and Adriana Kovashka. In 2nd Workshop on Sketch-Oriented Deep Learning, held in conjunction with the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2022. [pdf]

  • Emphasizing Complementary Samples for Non-literal Cross-modal Retrieval. Christopher Thomas and Adriana Kovashka. In 5th MUltimodal Learning and Applications Workshop, held in conjunction with the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2022. [pdf] [supp]

  • Doubling down: sparse grounding with an additional, almost-matching caption for detection-oriented multimodal pretraining. Giacomo Nebbia and Adriana Kovashka. In 5th MUltimodal Learning and Applications Workshop, held in conjunction with the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2022. [pdf]

  • Weakly-Supervised Action Detection Guided by Audio Narration. Keren Ye and Adriana Kovashka. In Joint 1st Ego4D and 10th EPIC Workshop, held in conjunction with the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2022. [pdf]

  • Visual Persuasion in COVID-19 Social Media Content: A Multi-Modal Characterization. Mesut Erhan Unal, Adriana Kovashka, Wen-Ting Chung and Yu-Ru Lin. In 1st International Workshop on Multimodal Understanding for the Web and Social Media (MUWS), held in conjunction with The WebConf (WWW), April 2022. [pdf]

  • 2021


  • Detecting Persuasive Atypicality by Modeling Contextual Compatibility. Meiqi Guo, Rebecca Hwa, and Adriana Kovashka. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), October 2021. [pdf] [supp]

  • Domain-robust VQA with diverse datasets and methods but no target labels. Mingda Zhang, Tristan Maidment, Ahmad Diab, Adriana Kovashka, Rebecca Hwa. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2021. [pdf]

  • Linguistic Structures as Weak Supervision for Visual Scene Graph Generation. Keren Ye and Adriana Kovashka. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2021. [pdf]

  • Predicting Visual Political Bias using Webly Supervised Data and an Auxiliary Task. Christopher Thomas and Adriana Kovashka. In International Journal of Computer Vision (IJCV) 2021. [preprint]

  • BasisNet: Two-stage Model Synthesis for Ecient Inference. Mingda Zhang, Chun-Te Chu, Andrey Zhmoginov, Andrew Howard, Brendan Jou, Yukun Zhu, Li Zhang, Rebecca Hwa, and Adriana Kovashka. In Proceedings of the Efficient Deep Learning for Computer Vision Workshop (ECV), held in conjunction with the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2021. (Best Paper Award.) [pdf]

  • Exploring Corruption Robustness: Inductive Biases in Vision Transformers and MLP-Mixers. Katelyn Morrison, Benjamin Gilby, Colton Lipchak, Adam Mattioli and Adriana Kovashka. In Uncertainty and Robustness in Deep Learning Workshop (UDL), held in conjunction with the International Conference on Machine Learning (ICML), July 2021. [pdf]

  • Capturing Student-Robot Interactions for a Data-Driven Educational Dialogue RL Environment. Tristan Maidment, Mingzhi Yu, Erin Walker, Adriana Kovashka, Diane Litman, and Timothy Nokes-Malach. In Reinforcement Learning for Education Workshop (EDM-RL), held in conjunction with the Educational Data Mining Conference, June 2021. [pdf]

  • Graph-Symbolic VQA with Rich Visual Estimators and No Question-Answer Labels. Zhexiong Liu and Adriana Kovashka. In Visual Question Answering Workshop, held in conjunction with the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2021. [pdf]

  • Image retrieval with mixed initiative and multimodal feedback. Nils Murrugarra-Llerena and Adriana Kovashka. In Computer Vision and Image Understanding (CVIU) Journal, March 2021. [link]

  • A Case Study of the Shortcut Effects in Visual Commonsense Reasoning. Keren Ye and Adriana Kovashka. In Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI), February 2021. [pdf]

  • Breaking Shortcuts by Masking for Robust Visual Reasoning. Keren Ye, Mingda Zhang and Adriana Kovashka. In Proceedings of the Winter Conference on Applications of Computer Vision (WACV), January 2021. [pdf] [supp]

  • 2020


  • Preserving Semantic Neighborhoods for Robust Cross-modal Retrieval. Christopher Thomas and Adriana Kovashka. In Proceedings of the European Conference on Computer Vision (ECCV), August 2020. [pdf] [video-short] [video-long]

  • SpotPatch: Parameter-Efficient Transfer Learning for Mobile Object Detection. Keren Ye, Adriana Kovashka, Mark Sandler, Menglong Zhu, Andrew Howard, Marco Fornoni. In Proceedings of the Asian Conference on Computer Vision (ACCV), December 2020. [pdf]

  • Context for Object Detection via Lightweight Global and Mid-level Representations. Mesut Erhan Unal and Adriana Kovashka. In Proceedings of the International Conference on Pattern Recognition (ICPR), January 2021. [pdf]

  • Syntharch: Interactive Image Search With Attribute-Conditioned Synthesis. Zac Yu and Adriana Kovashka. In Proceedings of the Diagram Image Retrieval and Analysis (DIRA), held in conjunction with the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2020. [pdf]

  • Story Completion With Explicit Modeling of Commonsense Knowledge. Mingda Zhang, Keren Ye, Rebecca Hwa and Adriana Kovashka. In Proceedings of Minds vs. Machines: How far are we from the common sense of a toddler?, held in conjunction with the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2020. [pdf]

  • Domain Generalization Using Shape Representation. Narges Honarvar Nazari and Adriana Kovashka. In Proceedings of Transferring and Adapting Source Knowledge in Computer Vision (TASK- CV), held in conjunction with European Conference on Computer Vision (ECCV), August 2020.

  • Classifying Nuclei Shape Heterogeneity in Breast Tumors with Skeletons. Brian Falkenstein, Adriana Kovashka, Seong Jae Hwang and S. Chakra Chennubhotla. In Proceedings of BioImage Computing, held in conjunction with European Conference on Computer Vision (ECCV), August 2020.

  • 2019


  • Interpreting the Rhetoric of Visual Advertisements. Keren Ye, Narges Honarvar Nazari, James Hahn, Zaeem Hussain, Mingda Zhang, Adriana Kovashka. In Transactions of Pattern Analysis and Machine Intelligence (TPAMI), 2019. [pdf]

  • Predicting the Politics of an Image Using Webly Supervised Data. Christopher Thomas and Adriana Kovashka. To appear, Proceedings of the Conference on Neural Information Processing Systems (NeurIPS), December 2019.     [pdf]     [supp]     [poster]     [data]

  • Cap2Det: Learning to Amplify Weak Caption Supervision for Object Detection. Keren Ye, Mingda Zhang, Adriana Kovashka, Wei Li, Danfeng Qin, Jesse Berent. To appear, Proceedings of the International Conference on Computer Vision (ICCV), October 2019.     [pdf]     [supp]     [poster]     [code]

  • Cross-Modality Personalization for Retrieval. Nils Murrugarra-Llerena and Adriana Kovashka. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2019. (Oral.)     [pdf]     [supp]     [poster]     [data]

  • Hiding in Plain Strokes: Handwriting and Applications to Steganography. James Hahn and Adriana Kovashka. In The Bright and Dark Sides of Computer Vision: Challenges and Opportunities for Privacy and Security (CV-COPS 2019), held in conjunction with the IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 2019. (Extended Abstract.)     [pdf]     [poster]

  • 2018


  • ADVISE: Symbolism and External Knowledge for Decoding Advertisements. Keren Ye and Adriana Kovashka. In Proceedings of the European Conference on Computer Vision (ECCV), September 2018.     [pdf]     [supp]     [related code]

  • Artistic Object Recognition by Unsupervised Style Adaptation. Christopher Thomas and Adriana Kovashka. Proceedings of the Asian Conference on Computer Vision (ACCV), December 2018.     [pdf]     [poster]     [project page]

  • Image Retrieval with Mixed Initiative and Multimodal Feedback. Nils Murrugarra-Llerena and Adriana Kovashka. In Proceedings of the British Machine Vision Conference (BMVC), September 2018. (Oral)     [pdf]     [supp]

  • Equal But Not The Same: Understanding the Implicit Relationship Between Persuasive Images and Text. Mingda Zhang, Rebecca Hwa and Adriana Kovashka. In Proceedings of the British Machine Vision Conference (BMVC), September 2018. (Spotlight)     [pdf]     [data]

  • Persuasive Faces: Generating Faces in Advertisements. Christopher Thomas and Adriana Kovashka. In Proceedings of the British Machine Vision Conference (BMVC), September 2018.     [pdf]     [supp]

  • Story Understanding in Video Advertisements. Keren Ye, Kyle Buettner, Adriana Kovashka. In Proceedings of the British Machine Vision Conference (BMVC), September 2018.     [pdf]     [data]

  • Asking Friendly Strangers: Non-Semantic Attribute Transfer. Nils Murrugarra-Llerena and Adriana Kovashka. Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI), February 2018.     [pdf]

  • 2017


  • Confidence and Diversity for Active Selection of Feedback in Image Retrieval. Bhavin Modi and Adriana Kovashka. In Proceedings of the British Machine Vision Conference (BMVC), September 2017.     [pdf]    

  • Automatic Understanding of Image and Video Advertisements. Zaeem Hussain, Mingda Zhang, Xiaozhong Zhang, Keren Ye, Christopher Thomas, Zuha Agha, Nathan Ong, Adriana Kovashka. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017. (Spotlight)     [pdf]     [supplementary]     [project page and dataset]     [visualization]     [poster]     [spotlight]

  • Learning Attributes from Human Gaze. Nils Murrugarra-Llerena and Adriana Kovashka. In Proceedings of IEEE Winter Conference on Applications of Computer Vision (WACV), March 2017.     [pdf]     [supplementary]     [project page]     [poster]     [slides]

  • Detecting Sexually Provocative Images. Debashis Ganguly, Mohammad H. Mofrad and Adriana Kovashka. In Proceedings of IEEE Winter Conference on Applications of Computer Vision (WACV), March 2017.     [pdf]     [poster]     [slides]

  • 2016


  • Crowdsourcing in Computer Vision. Adriana Kovashka, Olga Russakovsky, Kristen Grauman, Fei-Fei Li. In Foundations and Trends in Computer Graphics and Vision, NOW Publishers, 2016. [pdf]

  • Attributes for Image Retrieval. Adriana Kovashka and Kristen Grauman. In Visual Attributes (Advances in Computer Vision and Pattern Recognition), Springer, 2016.

  • Seeing Behind the Camera: Identifying the Authorship of a Photograph. Christopher Thomas and Adriana Kovashka. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016.     [pdf]     [supplementary]     [poster]     [project page]

  • A Visual Attention Algorithm Designed for Coupled Oscillator Acceleration. Christopher Thomas, Adriana Kovashka, Donald Chiarulli and Steven Levitan. In Proceedings of The Twelfth IEEE Embedded Vision Workshop, held in conjunction with the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016. (Oral)     [pdf]

  • Inferring Visual Persuasion via Body Language, Setting, and Deep Features. Xinyue Huang and Adriana Kovashka. In Proceedings of ChaLearn Looking at People and Faces of the World Challenge and Workshop, held in conjunction with the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016. (Oral)     [pdf]

  • Adapting Attributes by Selecting Features Similar across Domains. Siqi Liu and Adriana Kovashka. In Proceedings of IEEE Winter Conference on Applications of Computer Vision (WACV), March 2016.     [pdf]

  • 2015


  • WhittleSearch: Interactive Image Search with Relative Attribute Feedback. Adriana Kovashka, Devi Parikh and Kristen Grauman. International Journal of Computer Vision (IJCV), April 2015.     [link]

  • Discovering Attribute Shades of Meaning with the Crowd. Adriana Kovashka and Kristen Grauman. International Journal of Computer Vision (IJCV), January 2015.     [link]     [data]

  • 2014


  • Interactive Image Search with Attributes. Adriana Kovashka. PhD Thesis, 2014. [pdf]

  • Discovering Shades of Attribute Meaning with the Crowd. Adriana Kovashka and Kristen Grauman. Third International Workshop on Parts and Attributes, held in conjunction with the European Conference on Computer Vision (ECCV), September 2014.     [pdf]

  • Discovering Shades of Attribute Meaning with the Crowd. Adriana Kovashka and Kristen Grauman. Technical Report AI13-02, The University of Texas at Austin, November 5, 2013.     [pdf]

  • Interactive Image Search with Attribute-based Guidance and Personalization. Adriana Kovashka and Kristen Grauman. Workshop on Computer Vision and Human Computation, held in conjunction with the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2014.     [pdf]

  • 2013


  • Attribute Adaptation for Personalized Image Search. Adriana Kovashka and Kristen Grauman. Proceedings of the International Conference on Computer Vision (ICCV), December 2013.     [pdf]     [supplementary]     [poster]     [project page]

  • Attribute Pivots for Guiding Relevance Feedback in Image Search. Adriana Kovashka and Kristen Grauman. Proceedings of the International Conference on Computer Vision (ICCV), December 2013.     [pdf]     [supplementary]     [poster]     [project page]

  • 2012


  • WhittleSearch: Image Search with Relative Attribute Feedback. Adriana Kovashka, Devi Parikh and Kristen Grauman. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2012.    [pdf]    [supplementary]    [poster]    [project page]     [demo]

  • Relative Attributes for Enhanced Human-Machine Communication (Invited paper). Devi Parikh, Adriana Kovashka, Amar Parkash and Kristen Grauman. AAAI Conference on Artificial Intelligence (AAAI), July 2012.    [pdf]

  • 2011


  • Actively Selecting Annotations Among Objects and Attributes. Adriana Kovashka, Sudheendra Vijayanarasimhan and Kristen Grauman. Proceedings of the International Conference on Computer Vision (ICCV), November 2011.    [pdf]     [poster]     [video]     [project page]

  • 2010


  • Learning a Hierarchy of Discriminative Space-Time Neighborhood Features for Human Action Recognition. Adriana Kovashka and Kristen Grauman. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2010.   [pdf]   [project page]   [poster]

  • Authorship Attribution Using Probabilistic Context-Free Grammars. Sindhu Raghavan, Adriana Kovashka and Raymond Mooney. Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics (ACL), Short Papers, July 2010.   [pdf]

  • Human and Machine Detection of Stylistic Similarity in Art. Adriana Kovashka and Matthew Lease. CrowdConf 2010, October 2010.   [pdf]