Tuesday, 22 October 2024
The paper presented:
Mi Yan, Jiazhao Zhang, Yan Zhu, He Wang. MaskClustering: View Consensus based Mask Graph Clustering for Open-Vocabulary 3D Instance Segmentation.
Presented by Dr. Dragos Costea
Link to the paper: https://arxiv.org/pdf/2401.07745
Tuesday, 23 April 2024
The paper presented:
Lorenzo Lamberti, Elia Cereda, Gabriele Abbate, Lorenzo Bellone, Victor Javier Kartsch Morinigo, Michał Barcis, Agata Barcis, Alessandro Giusti, Francesco Conti, Daniele Palossi. "A Sim-to-Real Deep Learning-based Framework for Autonomous Nano-drone Racing".
Presented by Drd. Ing. Sebastian Mocanu
Link to the paper: https://arxiv.org/abs/2312.08991
Tuesday, 26 March 2024
The paper presented:
Bingxin Ke, Anton Obukhov, Shengyu Huang, Nando Metzger, Rodrigo Caye Daudt, Konrad Schindler. "Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation"
Presented by Dr. Dragos Costea
Link to the paper: https://arxiv.org/pdf/2312.02145.pdf
Project page: https://marigoldmonodepth.github.io/
Demo: https://huggingface.co/spaces/toshas/marigold
Tuesday, 12 March 2024
The paper presented:
Lihe Yang, Bingyi Kang2, Zilong Huang, Xiaogang Xu, Jiashi Feng, Hengshuang Zhao. “Depth Anything - Unleashing the Power of Large-Scale Unlabeled Data”
Presented by Dr. Dragos Costea
Link to the paper: https://arxiv.org/pdf/2401.10891.pdf
Project page: https://depth-anything.github.io/
Tuesday, 20 February 2024
The paper presented:
Wang, Z., Li, M., Xu, R., Zhou, L., Lei, J., Lin, X., ... & Ji, H. (2022). Language models with image descriptors have strong few-shot video-language learners. Advances in Neural Information Processing Systems, 35, 8483-8497.
Presented by Drd. Ing. Mihai Masala
Link to the paper: https://arxiv.org/pdf/2205.10747.pdf
Tuesday, 13 February 2024
The paper presented:
Wang, J., Yang, Z., Hu, X., Li, L., Lin, K., Gan, Z., ... & Wang, L. (2022). Git: A generative image-to-text transformer for vision and language. Transactions on Machine Learning Research 11/2022
Presented by Drd. Ing. Mihai Masala
Link to the paper: https://arxiv.org/pdf/2205.14100.pdf
Tuesday, 30 January 2024
He, X., Chen, S., Ma, F., Huang, Z., Jin, X., Liu, Z., ... & Feng, J. (2023).
"VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending" arXiv preprint arXiv:2305.13167.
Presented by Drd. Ing. Mihai Masala
Link to the paper: https://arxiv.org/pdf/2305.13167.pdf
Tuesday, 23 January 2024
Cho, Jang Hyun, Utkarsh Mall, Kavita Bala, and Bharath Hariharan.
"Picie: Unsupervised semantic segmentation using invariance and equivariance in clustering."
In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 16794-16804. 2021.
Presented by Prof. Univ. Dr. Marius Leordeanu
Link to the paper: https://openaccess.thecvf.com/.../Cho_PiCIE_Unsupervised...
Tuesday, January 09, 2024
Vatt: Transformers for multimodal self-supervised learning from raw video, audio and text. Advances in Neural Information Processing Systems, 34, pp. 24206-24221.
Akbari, H., Yuan, L., Qian, R., Chuang, W.H., Chang, S.F., Cui, Y. and Gong, B., 2021.
Presented by Prof. Univ. Dr. Marius Leordeanu
The paper can be found here: https://proceedings.neurips.cc/.../cb3213ada48302953cb0f1...
Tuesday, December 19, 2023
"4M: Massively Multimodal Masked Modeling"
David Mizrahi, Roman Bachmann, Oğuzhan Fatih Kar, Teresa Yeo, Mingfei Gao, Afshin Dehghan, Amir Zamir. NeuroIPS 2023
Presented by Prof. Univ. Dr. Marius Leordeanu
The paper can be found here: [2312.06647] 4M: Massively Multimodal Masked Modeling (arxiv.org)
Tuesday, December 12, 2023
"Multimae: Multi-modal multi-task masked autoencoders." In European Conference on Computer Vision, pp. 348-367. Cham: Springer Nature Switzerland, 2022. Bachmann, Roman, David Mizrahi, Andrei Atanov, and Amir Zamir.
Presented by Prof. Univ. Dr. Marius Leordeanu.
The paper can be found here: 2204.01678.pdf (arxiv.org)
Tuesday, November 28, 2023
"Distilling Self-Supervised Vision Transformers for Weakly-Supervised Few-Shot Classification & Segmentation." In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 19627-19638. 2023. Kang, Dahyun, Piotr Koniusz, Minsu Cho, and Naila Murray ( CVPR, 2023)
Presented by Prof.Univ.Dr. Marius Leordeanu.
The paper can be found here: CVPR 2023 Open Access Repository (thecvf.com)
Tuesday, November 21, 2023
"Test-time training with masked autoencoders." Gandelsman, Yossi, Yu Sun, Xinlei Chen, and Alexei Efros. (NEURIPS 2022)
Presented by Prof.Univ.Dr. Marius Leordeanu.
The paper can be found here: Test-Time Training with Masked Autoencoders (neurips.cc)
Tuesday, November 22, 2022
Recent advances in semi-supervised multi-task learning , Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans (ICCV 2021) and Semi-supervised Multi-task Learning for Semantics and Depth (WACV 2022)
Presented by Dragos Costea.
The paper can be found here.
Tuesday, 1 October 2019
A Generative Appearance Model for End-to-end Video Object Segmentation (CVPR 2019) and See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networks (CVPR 2019) Presented by Emanuela Haller.
The paper can be found here.
Tuesday, 24 September 2019
YouTube-VOS: Sequence-to-Sequence Video Object Segmentation (ECCV 2018) and RVOS: End-to-End Recurrent Network for Video Object Segmentation (CVPR 2019)
Presented by Emanuela Haller.
The presentation can be found here.
Tuesday, 6 August 2019 and Wednesday, 7 August 2019
"Tracking overview" presented by Elena Burceanu.
More details can be found here.
Tuesday, 4 June 2019
PReMVOS: Proposal-generation, Refinement and Merging for Video Object Segmentation (ACCV 2018) and Lucid Data Dreaming for Video Object Segmentation (JCV 2018)
Presented by Emanuela Haller.
The presentation can be found here.
Tuesday, 23 March 2019
"A Spectral Approach to Unsupervised Object Segmentation in Video"
Presented by Elena Burceanu.
The presentation can be found here.
Tuesday, 12 March 2019
A simple neural attentive meta-learner (ICLR 2018)
Presented by Armand Nicolicioiu.
Tuesday, 5 March 2019
Matching networks for one shot learning (NIPS 2016) and Model-agnostic meta-learning for fast adaptation of deep networks (ICML 2017)
Presented by Armand Nicolicioiu.
Tuesday, 26 February 2019
Siamese neural networks for one-shot image recognition (ICML Deep Learning Workshop 2015)
Presented by Armand Nicolicioiu.
Tuesday, 19 February 2019
Deep clustering for unsupervised learning of visual features (ECCV 2018)
Presented by Ioana Croitoru.
Tuesday, 12 February 2019
Hierarchically-attentive rnn for album summarization and storytelling (EMNLP 2017)
Presented by Vlad Bogolin.
The presentation can be found here.
Tuesday, 5 February 2019
Temporally grounding natural sentence in video (EMNLP 2018)
Presented by Vlad Bogolin.
The presentation can be found here.
Thursday, 31 January 2019
Object hallucination in image captioning (EMNLP 2018) and Learning to Evaluate Image Captioning (CVPR 2018)
Presented by Vlad Bogolin.
The presentation can be found here.
Tuesday, 15 January 2019
Polytope volume by descent in the face lattice and applications in social choice
Presented by Bogdan Ichim.
Tuesday, 4 December 2018
Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraints Presented by Mihai Pirvu.
Tuesday, 13 November 2018
Taskonomy: Disentangling Task Transfer Learning (CVPR 2018)
Presented by Bogdan Alexe.
The presentation can be found here.
Tuesday, 6 November 2018
Unsupervisedly Learned Latent Graphs as Transferable Representations (NIPS 2018)
Presented by Dan Oneata.
The presentation can be found here.
Tuesday, 23 October 2018
MaskRNN: Instance Level Video Object Segmentation (NIPS 2017) and Extending Layered Models to 3D Motion (ECCV 2018)
Presented by Emanuela Haller.
Tuesday, 16 October 2018
Instance Embedding Transfer to Unsupervised Video Object Segmentation, Unsupervised Video Object Segmentation with Motion-based Bilateral Networks and Unsupervised Video Object Segmentation using Motion Saliency-Guided Spatio-Temporal Propagation
Presented by Alina Marcu and Dragos Costea.
The presentation can be found here.
Tuesday, 9 October 2018
Interaction networks for learning about objects, relations and physics, Convolutional networks on graphs for learning molecular fingerprints, Semi-supervised classification withgraph convolutional networks, Gated graph sequence neural networks and Graph attention networks
Presented by Iulia Duta and Andrei Nicolicioiu.
Tuesday, 10 July 2018
3D-RCNN and Self-supervised Geometrically Stable Features
Presented by Dragos Costea.
Tuesday, 12 June 2018
Real-Time Deep Learning Method for Abandoned Luggage Detection in Video
Presented by Radu Ionescu.
The presentation can be found here.
Tuesday, 8 May 2018
Dynamic Routing Between Capsules presented by Razvan Condorovici.
Tuesday, 24 April 2018
CAM, GradCAM and GradCAM++ presented by Dragos Costea.
Tuesday, 17 April 2018
One-Shot Video Object Segmentation (CVPR 2017) and Online Adaptation of Convolutional Neural Networks for Video Object Segmentation
Presented by Emanuela Haller.
The presentation can be found here.
Tuesday, 3 April 2018
Learning a Robust Society of Tracking Parts using Co-occurrence Constraints (E. Burceanu and M. Leordeanu, 2018)
Presented by Elena Burceanu.
The presentation can be found here.
Tuesday, 27 March 2018
Speed/accuracy trade-offs for modern convolutional object detectors (CVPR 2017) si Optimizing the Trade-off between Single-Stage and Two-Stage Object Detectors using Image Difficulty Prediction
Presented by Petru Soviany.
Tuesday, 20 March 2018
Learning Video Object Segmentation with Visual Memory (P. Tokmakov et el)
Presented by Emanuela Haller.
The presentation can be found here.
Tuesday, 12 March 2018
Unsupervised Representation Learning by Sorting Sequences (H.Y Lee et al, ICCV 2017)
Presented by Ioana Croitoru.
Tuesday, 6 March 2018
Unsupervised Learning of Disentangled Representations from Video (E. Denton et al, NIPS 2017) presented by Alexandru Hulea.
Tuesday, 27 February 2018
SSH: Single Stage Headless Face Detector (M. Najibi et al, ICCV 2017)
Presented by Bogdan Alexe.
The presentation can be found here.
Tuesday, 20 February 2018
Speaking the Same Language: Matching Machine to Human Captions by Adversarial Training (R. Shetty et al, ICCV 2017)
Presented by Vlad Bogolin.
Tuesday, 13 February 2018
Deep Image Prior (D. Ulyanov et al) presented by Dan Oneata.
The presentation can be found here.
Tuesday, 6 February 2018
Deformable Convolutional Networks (J. Dai et al, ICCV 2017) presented by Iulian Felea.
Tuesday, 30 January 2018
Deep Value Networks Learn to Evaluate and Iteratively Refine Structured Outputs (M. Gygli et al, ICML 2017)
Presented by Radu Ionescu.
The presentation can be found here.
Tuesday, 23 January 2018
Learning by Association : A versatile semi-supervised training method for neural networks
Presented by Mihai Badea.
Tuesday, 16 January 2018
Introduction to Natural language processing presented by Marius Leordeanu.
Tuesday, 12 December 2017
Unsupervised Learning of Important Objects From First-Person Videos presented by Emanuela Haller.
Tuesday, 5 December 2017
Learning features by watching objects move presented by Ioana Croitoru.
Tuesday, 28 November 2017
Improved Image Captioning via Policy Gradient optimization of SPIDEr (S. Liu et al, ICCV 2017), Show, Adapt and Tell: Adversarial Training of Cross-domain Image Captioner (T.H. Chen et al, ICCV 2017) and Multi-Task Video Captioning with Video and Entailment Generation (R. Pasunuru et al, arXiv 2017)
Presented by Andrei Nicolicioiu
14 and 21 November 2017
Deep Visual-Semantic Alignments for Generating Image Descriptions (A. Karpathy et al, CVPR 2015) and Weakly Supervised Dense Video Captioning (Z. Shen et al, CVPR 2017)
Presented by Iulia Duta.
Tuesday, 7 November 2017
Densely Connected Convolutional Networks (G. Huang et al, CVPR 2017) presented by Corneliu Florea.
Tuesday, 10 October 2017
Creating Roadmaps in Aerial Images with Generative Adversarial Networks and Smoothing-based Optimization (D. Costea et al) presented by Dragos Costea.
Tuesday, 3 October 2017
Clockwork Convnets for Video Semantic Segmentation (E. Shelhamer et al) presented by Alina Marcu.
Tuesday, 26 September 2017
3D Bounding Box Estimation Using Deep Learning and Geometry (A. Mousavian et al) presented by Mihai Pîrvu.
Tuesday, 19 September 2017
You Only Look Once: Unified, Real-Time Object Detection (J. Redmon et al, CVPR 2016) P
Presented by Bogdan Alexe.
The presentation can be found here.
Tuesday, 12 September 2017
Dense-Captioning Events in Videos (R. Krishna et al) presented by Vlad Bogolin.
Tuesday, 5 September 2017
EmotioNet: An Accurate, Real-Time Algorithm for the Automatic Annotation of a Million Facial Expressions in the Wild (C. F. Benitez-Quiroz et al, CVPR 2016) presented by Laura Florea.
Tuesday, 18 July 2017
Learnable pooling with Context Gating for video classification (A. Miech et all) and Deep Convolutional Ranking forMultilabel Image Annotation (Y. Gong et al) presented by Andrei Nicolicioiu.
Tuesday, 4 July 2017
Computations of volumes and Ehrhart series in four candidates elections (W. Brunus et al) presented by Bogdan Ichim.
Tuesday, 27 June 2017
Detect2Rank :Combining Object Detectors UsingLearning to Rank (S. Karaoglu et al) presented by Ionut Felea.
Tuesday, 30 May 2017
A Discriminative Framework for Anomaly Detection in Large Videos (A. Del Giorno et al, ECCV 2016) and Unmasking the abnormal events in video (R. T. Ionescu et al, arXiv paper 2017)
Presented by Radu Ionescu.
The presentation can be found here.
Tuesday, 23 May 2017
Visual Attribute Transfer through Deep Image Analogy (J. Liao et al, arXiv paper 2017) presented by Mihai Badea.
Tuesday, 16 May 2017
The Pose Knows: Video Forecasting by Generating Pose Futures (J. Walker et al, arXiv paper 2017)
Presented by Marius Leordeanu.
Tuesday, 9 May 2017
Unsupervised Learning of Depth and Ego-Motion from Video (T. Zhou et al, CVPR 2017)
Presented by Emanuela Haller.
The presentation can be found here.
Tuesday, 2 May 2017
Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks (J.Y. Zhu et al) presented by Dragos Costea.
Tuesday, 25 April 2017
Unsupervised Learning for Physical Interaction through Video Prediction (C. Finn et al) and Unsupervised Learning of Long-Term Motion Dynamics for Videos (Z. Luo et al)
Presented by Ioana Croitoru.
The presentation can be found here.
Tuesday, 11 April 2017
"A Quest for Kleene Algebra in 2 Dimensions" (G. Stefanescu)
Presented by Gheorghe Stefanescu.
The presentation can be found here.
Tuesday, 4 April 2017
KCF (J. F. Henriques et al, PAMI 2015)
Presented by Elena Burceanu.
The presentation can be found here.
Tuesday, 28 March 2017
STRUCK (S. Hare et al, PAMI 2015)
Presented by Elena Burceanu.
The presentation can be found here.
Tuesday, 7 March 2017
Generative Adversarial Nets (I.J. Goodfellow et al, NIPS 2014) presented by Corneliu Florea.
Tuesday, 21 February 2017
Generative Adversarial Nets (I.J. Goodfellow et al, NIPS 2014) presented by Corneliu Florea.
Tuesday, 14 February 2017
Abnormal Event Detection at 150 FPS in MATLAB (C. Lu et al, ICCV 2013)
Presented by Bogdan Alexe.
The presentation can be found here.
Tuesday, 7 February 2017
Learning to Segment Object Candidates (P. Pinheiro et al, NIPS) and Learning to Refine Object Segments (P. Pinheiro et al)
Presented by Andrei Nicolicioiu.
The presentation can be found here.
Tuesday, 31 January 2017
Object contra Context: Dual Local-Global Semantic Segmentation in Aerial Images (Alina Marcu and Marius Leordeanu, AI-CAV 2017) presented by Alina Marcu.
Tuesday, 17 January 2017
Fully Convolutional Networks for Semantic Segmentation(J. Long et al, CVPR 2015)
Presented by Andrei Nicolicioiu.
The presentation can be found here.
Tuesday, 8 January 2017
Algorithmic principles of remote-PPG (Wang, W. et al) presented by Laura Florea.
The presentation can be found here.
Tuesday, 13 December 2016
Deep cascaded bi-network for face hallucination (Z. Shizhan et al, ECCV 2016)
Presented by Ionut Felea.
The presentation can be found here.
Tuesday, 6 December 2016
Voting theory (Analyzing the Practical Relevance of Voting Paradoxes via Ehrhart Theory, Computer Simulations, and Empirical Data - F. Brandt et al) presented by Bogdan Ichim.
Tuesday, 29 November 2016
Anticipating Visual Representations from Unlabeled Video(C. Vondrick, H. Pirsiavash and A. Torralba, CVPR 2016)
Presented by Vlad Bogolin.
The presentation can be found here.
Tuesday, 22 November 2016
How Hard Can It Be? Estimating the Difficulty of Visual Search in an Image (RT Ionescu, B Alexe, M Leordeanu, M Popescu, DP Papadopoulos, V Ferrari, CVPR 2016) and Weakly Supervised Object Localization Using Size Estimates (M Shi, V Ferrari, ECCV 2016)
Presented by Radu Ionescu.
The presentation can be found here.
Tuesday, 15 November 2016
Distilling the Knowledge in a Neural Network (G. Hinton et al), Do Deep Nets Really Need to be Deep (L. J. Ba et al, NIPS 2014) and Do Deep Convolutional Nets Really Need to be Deep and Convolutional? (G. Urban et al) Presented by Corneliu Florea.
The presentation can be found here.
Tuesday, 8 November 2016
A neural algorithm of artistic style (Gatys et al), Texture Synthesis Using Convolutional Neural Networks (Gatys et al, NIPS 2015) and Understanding Deep Image Representations by Inverting Them (Mahendran et al)
Presented by Mihai Badea
The presentation can be found here.
Tuesday, 1 November 2016
CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples (F. Radenovic, G. Tolias and O. Chum, ECCV 2016), Shuffle and Learn: Unsupervised Learning using Temporal Order Verification(I. Misra, L. Zitnick and M. Hebert, ECCV 2016) andUnsupervised Visual Representation Learning by Graph-based Consistent Constraints (D. Li, W. Hung, J. Huang, S. Wang, N. Ahuja and M. Yang, ECCV 2016) Presented by Marius Leordeanu
Tuesday, 25 October 2016
Identifying and attacking the saddle point problem in high-dimensional non-convex optimization (Y. Dauphin, R. Pascanu, C. Gulcehre, K. Cho, S. Ganguli, Y. Bengio, NIPS 2014)
Presented by Elena Burceanu.
The presentation can be found here.
Friday, 21 October 2016
Intriguing properties of neural networks (C. Szegedy, W. Zaremba, I. Sutskever, J. Bruna, D. Erhan, I. Goodfellow, R. Fergus, ICLR 2014), Explaining and Harnessing Adversarial Examples (I. J. Goodfellow, J. Shlens, C. Szegedy, ICLR 2015) and Distributional Smoothing with Virtual Adversarial Training (T. Miyato, S. Maeda, M. Koyama, K. Nakae, S. Ishii, ICLR 2016)
Presented by Elena Burceanu.
The presentation can be found here.
Friday, 14 October 2016
EMVS: Event-based Multi-View Stereo (H. Rebecq, G. Gallego and D. Scaramuzza, EMVS: Event-based Multi-View Stereo, BMVC 2016) and Simultaneous Optical Flow and Intensity Estimation from an Event Camera (P. Bardow, A. J. Davison and S. Leutenegger, Simultaneous Optical Flow and Intensity Estimation from an Event Camera, CVPR 2016)
Presented by Emanuela Haller.
The presentation can be found here.
Friday, 7 October 2016
ResNet (K. He, X. Zhang, S. Ren and J. Sun, Deep Residual Learning for Image Recognition, CVPR 2016) and FCNs (J. Long, E. Shelhamer and T. Darrell, Fully convolutional Networks for Semantic Segmentation, CVPR 2015)
Presented by Alina Marcu.
The presentation can be found here.
Wednesday, 28 September 2016
Faster R-CNN (S. Ren, K. He, R. Girshick, J. Sun, Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks, NIPS 2015)
Presented by Oana Parvan
The presentation can be found here.
Wednesday, 21 September 2016
R-CNN (R.Girshick, J. Donahue, T. Darrell, J. Malik, Rich feature hierarchies for accurate object detection and semantic segmentation, CVPR 2014) and the improved method Fast R-CNN (R. Girshick, Fast R-CNN, ICCV 2015)
Presented by Bogdan Alexe.
The presentation can be found here.
Wednesday, 14 September 2016
D. Costea, M. Leordeanu, Aerial image geolocalization from recognition and matching of roads and intersections, presented by Dragos Costea. He has some time problems with his method, so he also covered some possible improvements in this field inspired from this article.
The original article can be found here. The presentation can be found here.
Wednesday, 7 September 2016
K. Kang, W. Ouyang, H. Li, X. Wang, Object Detection from Video Tubelets with Convolutional Neural Networks, CVPR 2016
Presented by Ioana Croitoru.
The original article can be found here. The presentation can be found here.
Wednesday, 31 August 2016
R. Girshick, J. Donahue, T. Darrell, J. Malik, Rich feature hierarchies for accurate object detection and semantic segmentation, CVPR 2014
Presented by Bogdan Alexe.
The original article can be found here. The presentation can be found here.
Wednesday, 24 August 2016
C. Lu, J. Jia, C. Tang, Range-Sample Depth Feature for Action Recognition, CVPR 2014
Presented by Vlad Bogolin.
The original article can be found here. The presentation can be found here.