My name is Joao Carreira. I am a postdoctoral scholar in Prof. Jitendra Malik's group at EECS, UC Berkeley.
My research targets the development of techniques that make it possible to robustly recover rich and accurate descriptions of objects from a single image, in particular of their shapes. My full cv is here.
I did my Ph.D. with Prof. Cristian Sminchisescu in the formidable group he had at the University of Bonn, working on segmentation and recognition techniques. We did a
noise on the Pascal VOC Challenges.
Afterwards I did postdoctoral work in Prof. Jorge Batista's awesome group in ISR-Coimbra, with which I am also affiliated.
My full list of publications and corresponding bibtex files can be consulted on my google scholar account .
Email: carreira at eecs.berkeley.edu
- My invited talk at SIBGRAPI 2015 about feedback for human pose estimation and 3D reconstruction is available on youtube.
- Three papers accepted in ICCV 2015.
- We have made available testing code for "Human Pose Estimation with Iterative Error Feedback". Check below.
- My project "Shape-Centric Visual Representation Learning" will be funded by the Portuguese Science Foundation (FCT).
- Congrats are due to Abhishek and Shubham for the Best Student Paper Award at
- Two papers accepted in CVPR 2015, one for oral presentation.
- I am co-organizing the 3D from a Single Image workshop at CVPR 2015. A preliminary list of speakers and the call for papers can be found here.
- It will be my great pleasure to serve as an invited speaker at SIBGRAPI 2015 in Salvador, Brazil.
- Extended version of the second-order pooling paper accepted at TPAMI.
- Taught an image segmentation course with Cristian Sminchisescu at the VISUM 2014 summer school.
- Paper accepted at IROS 2014.
- Two papers accepted for oral presentation at CVPR 2014.
- Our ICCV 2013 paper received the prestigious Thumbs-up from Tombone award. Thanks Tomasz. ;-)
- US patent pending for "Semantic Segmentation Method with Second-Order Pooling".
- Paper accepted in IJCV.
- Paper accepted for oral presentation at ICCV 2013.
- Got selected for the CVPR 2013 Doctoral Consortium and awarded a travel grant.
- Paper accepted at CVPR 2013.
- Graduated! Thesis available.
J. Carreira*, S. Vicente*, L. Agapito and J. Batista. Lifting Object Detection Datasets into 3D.
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) Special Issue CVPR 2014. To appear, 2015. (* first two authors contributed equally) pdf
J. Carreira, R. Caseiro, J. Batista and C. Sminchisescu. Free-Form Region Description with Second-Order Pooling.
Transactions on Pattern Analysis and Machine Intelligence (TPAMI), June 2015. pdf
A. Ion, J. Carreira and C. Sminchisescu. Probabilistic Joint Image
Segmentation and Labeling by Figure-Ground Composition.
International Journal of Computer Vision (IJCV), March 2014. pdf
J. Carreira and C. Sminchisescu. CPMC: Automatic Object Segmentation Using Constrained Parametric Min-Cuts.
In IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), July 2012. pdf project/code
J. Carreira*, F. Li* and C. Sminchisescu. Object Recognition by Sequential Figure-Ground Ranking.
In International Journal of Computer Vision (IJCV), July 2012. (* first two authors contributed equally) pdf
A. Kar, S. Tulsiani, J. Carreira, and J. Malik. Amodal Completion and Size Constancy in Natural Scenes.
In ICCV 2015. pdf
P. Agrawal, J. Carreira, and J. Malik. Learning to See by Moving.
In ICCV 2015. arxiv version project/code
S. Tulsiani, J. Carreira, and J. Malik. Pose Induction for Novel Object Categories.
In ICCV 2015. pdf arxiv version code
J. Carreira, A. Kar, S. Tulsiani and J. Malik. Virtual View Networks for Object Reconstruction.
In CVPR 2015. pdf project/code
A. Kar*, S. Tulsiani*, J. Carreira and J. Malik. Category-Specific Object Reconstruction from a Single Image. [Oral] [Best Student Paper Award]
In CVPR 2015. (*first two authors contributed equally) pdf project/code
C. Premebida, J. Carreira, J. Batista, U. Nunes. Pedestrian Detection Combining RGB and Dense Lidar Data.
In IROS 2014. pdf
S. Vicente*, J. Carreira*, L. Agapito and J. Batista. Reconstructing
PASCAL VOC. [Oral]
In CVPR 2014. (* first two authors contributed equally) pdf supp. material project/code
C. Ionescu, J. Carreira and C. Sminchisescu. Iterated Second-Order
Label Sensitive Pooling for 3D Human Pose Estimation. [Oral]
In CVPR 2014. pdf project
J. F. Henriques, J. Carreira, R. Caseiro, J. Batista. Beyond Hard Negative Mining: Efficient Detector Learning via Block-Circulant Decomposition. [Oral]
In ICCV 2013. pdf supp. material project/code
F. Li, J. Carreira, G. Lebanon, C. Sminchisescu. Composite Statistical Inference for Semantic Segmentation.
In CVPR 2013.
J. Carreira, R. Caseiro, J. Batista and C. Sminchisescu. Semantic Segmentation with Second-Order Pooling. [Oral]
In ECCV 2012. pdf project/code slides talk
A. Ion, J. Carreira and C. Sminchisescu. Probabilistic Joint Image Segmentation and Labeling. [Spotlight presentation]
In NIPS 2011. pdf
A. Ion, J. Carreira and C. Sminchisescu. Image Segmentation by Figure-Ground Composition into Maximal Cliques.
In ICCV 2011. pdf supp. material
J. Carreira and C. Sminchisescu. Constrained Parametric Min-Cuts for Automatic Object Segmentation.
In CVPR 2010. pdf
F. Li*, J. Carreira* and C. Sminchisescu. Object Recognition as Ranking Holistic Figure-Ground Hypotheses.
In CVPR 2010. (* first two authors contributed equally) pdf
J. Carreira, P. Agrawal, K. Fragkiadaki and J. Malik. Human Pose Estimation with Iterative Error Feedback.
arXiv, July 2015. pdf project/code
J. Carreira. Bottom-Up Object Segmentation for Visual Recognition.
Doctoral Thesis. University of Bonn, December 2012. pdf
J. Carreira, A. Ion and C. Sminchisescu. Image Segmentation by Discounted Cumulative Ranking on Maximal Cliques.
Technical Report 06-2010 (arXiv:1009.4823), Computer Vision and Machine Learning Group, Institute for Numerical Simulation, University of Bonn, June 2010. pdf
J. Carreira, F. Li and C. Sminchisescu. Object Recognition by Ranking Figure-Ground Hypotheses.
Snowbird Learning, April 2010.pdf