Anna Kukleva

I’m Anna Kukleva, a PhD student at Computer Vision and Machine Learning department at Max Plank Institute for Informatics supervised by Bernt Schiele. My research involves close collaborations with Hilde Kuehne (Bonn), and Christian Rupprecht (Oxford). During my PhD, 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

profile photo

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:     Serve 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

01/23:     1 paper accepted at ICLR 2023

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


HowToCaption: Prompting LLMs to Transform Video Annotations at Scale
Nina Shvetsova*, Anna Kukleva*, Xudong Hong, Christian Rupprecht, Bernt Schiele, Hilde Kuehne
(*equal contribution)
ArXiv, 2023

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



Revisiting Consistency Regularization for Semi-Supervised Learning
Yue Fan, Anna Kukleva, Bernt Schiele
IJCV, 2023



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



TAEC: Unsupervised Action Segmentation with Temporal-Aware Embedding and Clustering
Wei Lin, Anna Kukleva, Horst Possegger, Hilde Kuehne, Horst Bischof
CEUR Workshop, 2023



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



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



Stolen from Jon Barron. Big thanks!