Anna Kukleva

Anna Kukleva

I’m Anna Kukleva, a postdoctoral researcher at MPII. I received my a PhD at Computer Vision and Machine Learning department at Max Plank Institute for Informatics, where I was supervised by Bernt Schiele and was honored with the Otto-Hahn-Medal for an outstanding PhD thesis. During my PhD, my research involved close collaborations with Hilde Kuehne (Tuebingen AI Center), and Christian Rupprecht (Oxford). I’ve visited Meta FAIR and FRL labs as research intern. Particularly, in Nimble XR Input team at FRL, we were working on egocentric videos with Fadime Sener. Prior to my PhD, I had the opportunity to work in WILLOW team at Inria Paris on multi-modal understanding of social human behaviour with Makarand Tapaswi and Ivan Laptev. During my master, I’ve been working on unsupervised video segmentation in Uni Bonn in the lab of Jürgen Gall.

My research focuses on image and multi-modal video recognition, with a specific interest in learning representations through self-supervised, semi-supervised, and rarely fully-supervised methods. My focus extends to exploring the transferability of these methods to few-shot and open-set generalization scenarios.

Email / CV / Google Scholar / Github / LinkedIn

News

12/25: 1 paper accepted at WACV 2026! Thanks to Siarhei and Dhimitrios!
11/25: I'll serve as Area Chair for ICML 2026
10/25: Visited Visual Recognition Group (VRG) and talked about "Unconventional LLM usage in vision tasks" at the 50th PRCVC
10/25: Reviewer of the Month at Nature, Communications Engineering
07/25: Our workshop "NextVid" is accepted to NeurIPS 2025! Stay tuned!
07/25: I'll serve as Area Chair for WACV 2026
06/25: Honorod to receive the Otto-Hahn-Medal for my PhD thesis
04/25: I'll serve as Area Chair for NeurIPS 2025
02/25: 2 papers accepted at CVPR 2025! Thanks to Felix, Philipp, and Moritz!
02/25: I'll serve as Doctoral Consortium Chair for ICCV 2025
02/25: Our workshop "What is Next in Multimodal Foundation Models?" is accepted to CVPR25! Stay tuned!
02/25: Visited FunAI group and talked about "Advancing Video Recognition with Less Supervision"
08/24: Gave Research Spotlight Talk at GCPR 2024
08/24: Defended my PhD! 🎉 👩‍🎓
07/24: Nina and I talk about HowToCaption, watch here Twelve Labs
07/24: Gave a talk on learning with less supervision at SprintML, CISPA
07/24: 1 paper accepted at ECCV 2024!
06/24: I'll serve as Area Chair for WACV 2025
06/24: Top reviewer at CVPR 2024
03/24: Got accepted to Doctoral Consortium at CVPR24
03/24: Gave a talk on learning with less supervision at VGG Reading Group, Oxford
03/24: Gave a talk on learning with less supervision at University of Siegen
02/24: 2 papers accepted at CVPR 2024!
12/23: Our workshop "LPVL" is accepted to CVPR24! Stay tuned!
11/23: Top reviewer at NeurIPS 2023
08/23: Served as Area Chair for WACV 2024
07/23: 3 papers accepted at ICCV 2023!
05/23: Joined Meta FRL as a research intern. Working with Fadime Sener
02/23: Top reviewer at AISTAT 2023

Publications

MM-TS

MM-TS: Multi-Modal Temperature and Margin Schedules for Contrastive Learning with Long-Tail Data
Siarhei Sheludzko, Dhimitrios Duka, Bernt Schiele, Hilde Kuehne, Anna Kukleva
WACV 2026

RefAM

RefAM: Attention Magnets for Zero-Shot Referral Segmentation
Anna Kukleva*, Enis Simsar*, Alessio Tonioni, Muhammad Ferjad Naeem, Federico Tombari, Jan Eric Lenssen, Bernt Schiele
(*equal contribution)
preprint, arxiv 2025

	Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs Selim Kuzucu, Muhammad Ferjad Naeem, Anna Kukleva, Federico Tombari, Bernt Schiele preprint, arxiv 2025 Paper
	T-FAKE: Synthesizing Thermal Images for Facial Landmarking Philipp Flotho, Moritz Piening, Anna Kukleva, Gabriele Steidl (equal contribution) CVPR, 2025* Paper \| Dataset
	VideoGEM: Training-free Action Grounding in Videos Felix Vogel, Walid Bousselham, Anna Kukleva, Nina Shvetsova, Hilde Kuehne CVPR, 2025 Paper \| Code
	HowToCaption: Prompting LLMs to Transform Video Annotations at Scale Nina Shvetsova, Anna Kukleva, Xudong Hong, Christian Rupprecht, Bernt Schiele, Hilde Kuehne (equal contribution) ECCV, 2024* Paper \| Code
	X-MIC: Cross-Modal Instance Conditioning for Egocentric Action Generalization Anna Kukleva, Fadime Sener, Edoardo Remelli, Bugra Tekin, Eric Sauser , Bernt Schiele, Shugao Ma CVPR, 2024 Paper \| Code
	OrCo: Towards Better Generalization via Orthogonality and Contrast for Few-Shot Class-Incremental Learning Noor Ahmed, Anna Kukleva, Bernt Schiele (equal contribution) CVPR, 2024 (Highlight)* Paper \| Code
	In-Style: Bridging Text and Uncurated Videos with Style Transfer for Text-Video Retrieval Nina Shvetsova, Anna Kukleva, Bernt Schiele, Hilde Kuehne (equal contribution) ICCV, 2023* Paper \| Code
	SSB: Simple but Strong Baseline for Boosting Performance of Open-Set Semi-Supervised Learning Yue Fan, Anna Kukleva, Dengxin Dai, Bernt Schiele ICCV, 2023 Paper \| Code
	Learning by Sorting: Self-supervised Learning with Group Ordering Constraints Nina Shvetsova, Felix Petersen, Anna Kukleva, Bernt Schiele, Hilde Kuehne ICCV, 2023 Paper
	Revisiting Consistency Regularization for Semi-Supervised Learning Yue Fan, Anna Kukleva, Bernt Schiele IJCV, 2023 Paper
	Temperature Schedules for self-supervised contrastive methods on long-tail data Anna Kukleva, Moritz Boehle, Bernt Schiele, Hilde Kuehne, Christian Rupprecht (equal contribution) ICLR, 2023* Paper \| Code
	Leveraging Self-Supervised Training for Unintentional Action Recognition Enea Duka, Anna Kukleva, Bernt Schiele (equal contribution) ECCVW, 2022* Paper \| Code
	CycDA: Unsupervised Cycle Domain Adaptation from Image to Video Wei Lin, Anna Kukleva, Kunyang Sun, Horst Possegger, Hilde Kuehne, Horst Bischof ECCV, 2022 Paper
	TAEC: Unsupervised Action Segmentation with Temporal-Aware Embedding and Clustering Wei Lin, Anna Kukleva, Horst Possegger, Hilde Kuehne, Horst Bischof CEUR Workshop, 2023 Paper
	CoSSL: Co-Learning of Representation and Classifier for Imbalanced Semi-Supervised Learning Yue Fan, Dengxin Dai, Anna Kukleva, Bernt Schiele CVPR, 2022 Paper \| Code
	Generalized and Incremental Few-Shot Learning by Explicit Learning and Calibration Without Forgetting Anna Kukleva, Hilde Kuehne, Bernt Schiele ICCV, 2021 Paper \| Code
	Joint Visual-Temporal Embedding for Unsupervised Learning of Actions in Untrimmed Sequences Rosaura G. VidalMata, Walter J. Scheirer, Anna Kukleva, David Cox, Hilde Kuehne WACV, 2021 Paper
	Learning Interactions and Relationships between Movie Characters Anna Kukleva, Makarand Tapaswi, Ivan Laptev CVPR, 2020 (Oral) Paper \| Code
	Utilizing Temporal Information in Deep Convolutional Network for Efficient Soccer Ball Detection and Tracking Anna Kukleva, Mohammad Asif Khan, Hafez Farazi, Sven Behnke (equal contribution) RoboCup, 2019 (Oral)* Paper \| Code
	Unsupervised Learning of Action Classes with Continuous Temporal Embedding Anna Kukleva, Hilde Kuehne, Fadime Sener, Jürgen Gall (equal contribution) CVPR, 2019* Paper \| Code

Talks

10/2025: Visited Visual Recognition Group (VRG) and talked about "Unconventional LLM usage in vision tasks" at the 50th Pattern Recognition and Computer Vision Colloquium , Czech Technical University, Prague
02/2025: Talk on advancing video recognition with less supervision at FunAI group, UTN
09/2024: Research Spotlight Talk at GCPR 2024
08/2024: "HowToCaption: Prompting LLMs to Transform Video Annotations at Scale" at The 57th session of MultimodalWeekly Twelve Labs
07/2024: Talk on learning with less supervision at SprintML, CISPA
03/2024: Talk on learning with less supervision at VGG Reading Group, Oxford
03/2024: Talk on learning with less supervision at University of Siegen
02/2024: Moderate Q&A session of amazing talk by Yuxiong Wang who talks about "Bridging Generative & Discriminative Learning in the Open Worlds", Virtual
01/2022: Talk at Compuer Vision Talks, Virtual
12/2020: Talk at 6th Christmas Colloquium on Computer Vision 2020, Samsung AI Center Moscow, Virtual
08/2020: Talk at DLCV Practioner’s Evening, Virtual
01/2020: Talk at Abhinav Gupta’s group at CMU in Pittsburgh, USA
11/2019: Talk at WILLOW-ENPC-Berkeley Workshop on Vision and Robotics in Paris, France
09/2019: Poster at BMVA symposium on Video Understanding in London, UK
06/2019: Poster at WiCV workshop in conjunction with CVPR 2019 in Long Beach, USA

Academic

Doctoral Consortium Chair: ICCV 2025
Area Chair: WACV24-26, NeurIPS25, ICML26
Top Reviewer: AISTAT23, NeurIPS23, CVPR24
Reviewer: CVPR21-26 (w/o 25), ICCV21-23, ECCV22-24, AISTAT23, NeurIPS23-24, ICML25, WACV21-22, PAMI, IJCV, TMM, ACMMM21, Nature Commseng
10/2025: Reviewer of the Month: Nature CommsEng
06/2025: Otto-Hahn-Medal (PhD Thesis Award), Max-Planck-Gesellschaft
07/2021: Grace-Hopper-Award (Master Thesis Award), Uni Bonn
ECCV 2020: Coorganizing the WiCV workshop, Virtual
CVPR 2024: Coorganizing workshop "Learning from Procedural Videos and Language: What is Next?", Seattle
CVPR 2025: Coorganizing workshop "MMFM3: The 3rd Workshop on What is Next in Multimodal Foundation Models?", San Diego
NeurIPS 2025: Coorganizing workshop "(NextVid) What Makes a Good Video: Next Practices in Video Generation and Evaluation" , Nashville

Stolen from Jon Barron. Big thanks!