Alert button
Picture for Vladan Radosavljevic

Vladan Radosavljevic

Alert button

Multi-Modal Trajectory Prediction of NBA Players

Aug 18, 2020
Sandro Hauri, Nemanja Djuric, Vladan Radosavljevic, Slobodan Vucetic

Figure 1 for Multi-Modal Trajectory Prediction of NBA Players
Figure 2 for Multi-Modal Trajectory Prediction of NBA Players
Figure 3 for Multi-Modal Trajectory Prediction of NBA Players
Figure 4 for Multi-Modal Trajectory Prediction of NBA Players

National Basketball Association (NBA) players are highly motivated and skilled experts that solve complex decision making problems at every time point during a game. As a step towards understanding how players make their decisions, we focus on their movement trajectories during games. We propose a method that captures the multi-modal behavior of players, where they might consider multiple trajectories and select the most advantageous one. The method is built on an LSTM-based architecture predicting multiple trajectories and their probabilities, trained by a multi-modal loss function that updates the best trajectories. Experiments on large, fine-grained NBA tracking data show that the proposed method outperforms the state-of-the-art. In addition, the results indicate that the approach generates more realistic trajectories and that it can learn individual playing styles of specific players.

* Accepted Paper at WACV 2021 
Viaarxiv icon

Predicting Motion of Vulnerable Road Users using High-Definition Maps and Efficient ConvNets

Jun 20, 2019
Fang-Chieh Chou, Tsung-Han Lin, Henggang Cui, Vladan Radosavljevic, Thi Nguyen, Tzu-Kuo Huang, Matthew Niedoba, Jeff Schneider, Nemanja Djuric

Figure 1 for Predicting Motion of Vulnerable Road Users using High-Definition Maps and Efficient ConvNets
Figure 2 for Predicting Motion of Vulnerable Road Users using High-Definition Maps and Efficient ConvNets
Figure 3 for Predicting Motion of Vulnerable Road Users using High-Definition Maps and Efficient ConvNets
Figure 4 for Predicting Motion of Vulnerable Road Users using High-Definition Maps and Efficient ConvNets

Following detection and tracking of traffic actors, prediction of their future motion is the next critical component of a self-driving vehicle (SDV) technology, allowing the SDV to operate safely and efficiently in its environment. This is particularly important when it comes to vulnerable road users (VRUs), such as pedestrians and bicyclists. These actors need to be handled with special care due to an increased risk of injury, as well as the fact that their behavior is less predictable than that of motorized actors. To address this issue, in this paper we present a deep learning-based method for predicting VRU movement, where we rasterize high-definition maps and actor's surroundings into bird's-eye view image used as an input to deep convolutional networks. In addition, we propose a fast architecture suitable for real-time inference, and present a detailed ablation study of various rasterization choices. The results strongly indicate benefits of using the proposed approach for motion prediction of VRUs, both in terms of accuracy and latency.

* Shortened version accepted at the workshop on 'Machine Learning for Intelligent Transportation Systems' at Conference on Neural Information Processing Systems (MLITS), Montreal, Canada, 2018 
Viaarxiv icon

Multimodal Trajectory Predictions for Autonomous Driving using Deep Convolutional Networks

Mar 01, 2019
Henggang Cui, Vladan Radosavljevic, Fang-Chieh Chou, Tsung-Han Lin, Thi Nguyen, Tzu-Kuo Huang, Jeff Schneider, Nemanja Djuric

Figure 1 for Multimodal Trajectory Predictions for Autonomous Driving using Deep Convolutional Networks
Figure 2 for Multimodal Trajectory Predictions for Autonomous Driving using Deep Convolutional Networks
Figure 3 for Multimodal Trajectory Predictions for Autonomous Driving using Deep Convolutional Networks
Figure 4 for Multimodal Trajectory Predictions for Autonomous Driving using Deep Convolutional Networks

Autonomous driving presents one of the largest problems that the robotics and artificial intelligence communities are facing at the moment, both in terms of difficulty and potential societal impact. Self-driving vehicles (SDVs) are expected to prevent road accidents and save millions of lives while improving the livelihood and life quality of many more. However, despite large interest and a number of industry players working in the autonomous domain, there still remains more to be done in order to develop a system capable of operating at a level comparable to best human drivers. One reason for this is high uncertainty of traffic behavior and large number of situations that an SDV may encounter on the roads, making it very difficult to create a fully generalizable system. To ensure safe and efficient operations, an autonomous vehicle is required to account for this uncertainty and to anticipate a multitude of possible behaviors of traffic actors in its surrounding. We address this critical problem and present a method to predict multiple possible trajectories of actors while also estimating their probabilities. The method encodes each actor's surrounding context into a raster image, used as input by deep convolutional networks to automatically derive relevant features for the task. Following extensive offline evaluation and comparison to state-of-the-art baselines, the method was successfully tested on SDVs in closed-course tests.

* Accepted for publication at IEEE International Conference on Robotics and Automation (ICRA) 2019 
Viaarxiv icon

Short-term Motion Prediction of Traffic Actors for Autonomous Driving using Deep Convolutional Networks

Sep 16, 2018
Nemanja Djuric, Vladan Radosavljevic, Henggang Cui, Thi Nguyen, Fang-Chieh Chou, Tsung-Han Lin, Jeff Schneider

Figure 1 for Short-term Motion Prediction of Traffic Actors for Autonomous Driving using Deep Convolutional Networks
Figure 2 for Short-term Motion Prediction of Traffic Actors for Autonomous Driving using Deep Convolutional Networks
Figure 3 for Short-term Motion Prediction of Traffic Actors for Autonomous Driving using Deep Convolutional Networks
Figure 4 for Short-term Motion Prediction of Traffic Actors for Autonomous Driving using Deep Convolutional Networks

Despite its ubiquity in our daily lives, AI is only just starting to make advances in what may arguably have the largest societal impact thus far, the nascent field of autonomous driving. In this work we discuss this important topic and address one of crucial aspects of the emerging area, the problem of predicting future state of autonomous vehicle's surrounding necessary for safe and efficient operations. We introduce a deep learning-based approach that takes into account current world state and produces rasterized representations of each actor's vicinity. The raster images are then used by deep convolutional models to infer future movement of actors while accounting for inherent uncertainty of the prediction task. Extensive experiments on real-world data strongly suggest benefits of the proposed approach. Moreover, following successful tests the system was deployed to a fleet of autonomous vehicles.

Viaarxiv icon

Proceedings of the 2017 AdKDD & TargetAd Workshop

Jul 11, 2017
Abraham Bagherjeiran, Nemanja Djuric, Mihajlo Grbovic, Kuang-Chih Lee, Kun Liu, Vladan Radosavljevic, Suju Rajan

Proceedings of the 2017 AdKDD and TargetAd Workshop held in conjunction with the 23rd ACM SIGKDD Conference on Knowledge Discovery and Data Mining Halifax, Nova Scotia, Canada.

* Workshop Proceedings with links to the accepted papers 
Viaarxiv icon

Scalable Semantic Matching of Queries to Ads in Sponsored Search Advertising

Jul 07, 2016
Mihajlo Grbovic, Nemanja Djuric, Vladan Radosavljevic, Fabrizio Silvestri, Ricardo Baeza-Yates, Andrew Feng, Erik Ordentlich, Lee Yang, Gavin Owens

Figure 1 for Scalable Semantic Matching of Queries to Ads in Sponsored Search Advertising
Figure 2 for Scalable Semantic Matching of Queries to Ads in Sponsored Search Advertising
Figure 3 for Scalable Semantic Matching of Queries to Ads in Sponsored Search Advertising
Figure 4 for Scalable Semantic Matching of Queries to Ads in Sponsored Search Advertising

Sponsored search represents a major source of revenue for web search engines. This popular advertising model brings a unique possibility for advertisers to target users' immediate intent communicated through a search query, usually by displaying their ads alongside organic search results for queries deemed relevant to their products or services. However, due to a large number of unique queries it is challenging for advertisers to identify all such relevant queries. For this reason search engines often provide a service of advanced matching, which automatically finds additional relevant queries for advertisers to bid on. We present a novel advanced matching approach based on the idea of semantic embeddings of queries and ads. The embeddings were learned using a large data set of user search sessions, consisting of search queries, clicked ads and search links, while utilizing contextual information such as dwell time and skipped ads. To address the large-scale nature of our problem, both in terms of data and vocabulary size, we propose a novel distributed algorithm for training of the embeddings. Finally, we present an approach for overcoming a cold-start problem associated with new ads and queries. We report results of editorial evaluation and online tests on actual search traffic. The results show that our approach significantly outperforms baselines in terms of relevance, coverage, and incremental revenue. Lastly, we open-source learned query embeddings to be used by researchers in computational advertising and related fields.

* 39th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2016, Pisa, Italy  
* 10 pages, 4 figures, 39th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2016, Pisa, Italy 
Viaarxiv icon

Non-linear Label Ranking for Large-scale Prediction of Long-Term User Interests

Jun 29, 2016
Nemanja Djuric, Mihajlo Grbovic, Vladan Radosavljevic, Narayan Bhamidipati, Slobodan Vucetic

Figure 1 for Non-linear Label Ranking for Large-scale Prediction of Long-Term User Interests
Figure 2 for Non-linear Label Ranking for Large-scale Prediction of Long-Term User Interests
Figure 3 for Non-linear Label Ranking for Large-scale Prediction of Long-Term User Interests
Figure 4 for Non-linear Label Ranking for Large-scale Prediction of Long-Term User Interests

We consider the problem of personalization of online services from the viewpoint of ad targeting, where we seek to find the best ad categories to be shown to each user, resulting in improved user experience and increased advertisers' revenue. We propose to address this problem as a task of ranking the ad categories depending on a user's preference, and introduce a novel label ranking approach capable of efficiently learning non-linear, highly accurate models in large-scale settings. Experiments on a real-world advertising data set with more than 3.2 million users show that the proposed algorithm outperforms the existing solutions in terms of both rank loss and top-K retrieval performance, strongly suggesting the benefit of using the proposed model on large-scale ranking problems.

* 28th AAAI Conference on Artificial Intelligence (AAAI-14) 
Viaarxiv icon

Hierarchical Neural Language Models for Joint Representation of Streaming Documents and their Content

Jun 28, 2016
Nemanja Djuric, Hao Wu, Vladan Radosavljevic, Mihajlo Grbovic, Narayan Bhamidipati

Figure 1 for Hierarchical Neural Language Models for Joint Representation of Streaming Documents and their Content
Figure 2 for Hierarchical Neural Language Models for Joint Representation of Streaming Documents and their Content
Figure 3 for Hierarchical Neural Language Models for Joint Representation of Streaming Documents and their Content
Figure 4 for Hierarchical Neural Language Models for Joint Representation of Streaming Documents and their Content

We consider the problem of learning distributed representations for documents in data streams. The documents are represented as low-dimensional vectors and are jointly learned with distributed vector representations of word tokens using a hierarchical framework with two embedded neural language models. In particular, we exploit the context of documents in streams and use one of the language models to model the document sequences, and the other to model word sequences within them. The models learn continuous vector representations for both word tokens and documents such that semantically similar documents and words are close in a common vector space. We discuss extensions to our model, which can be applied to personalized recommendation and social relationship mining by adding further user layers to the hierarchy, thus learning user-specific vectors to represent individual preferences. We validated the learned representations on a public movie rating data set from MovieLens, as well as on a large-scale Yahoo News data comprising three months of user activity logs collected on Yahoo servers. The results indicate that the proposed model can learn useful representations of both documents and word tokens, outperforming the current state-of-the-art by a large margin.

* 24th International World Wide Web Conference 
Viaarxiv icon

Network-Efficient Distributed Word2vec Training System for Large Vocabularies

Jun 27, 2016
Erik Ordentlich, Lee Yang, Andy Feng, Peter Cnudde, Mihajlo Grbovic, Nemanja Djuric, Vladan Radosavljevic, Gavin Owens

Figure 1 for Network-Efficient Distributed Word2vec Training System for Large Vocabularies
Figure 2 for Network-Efficient Distributed Word2vec Training System for Large Vocabularies
Figure 3 for Network-Efficient Distributed Word2vec Training System for Large Vocabularies
Figure 4 for Network-Efficient Distributed Word2vec Training System for Large Vocabularies

Word2vec is a popular family of algorithms for unsupervised training of dense vector representations of words on large text corpuses. The resulting vectors have been shown to capture semantic relationships among their corresponding words, and have shown promise in reducing a number of natural language processing (NLP) tasks to mathematical operations on these vectors. While heretofore applications of word2vec have centered around vocabularies with a few million words, wherein the vocabulary is the set of words for which vectors are simultaneously trained, novel applications are emerging in areas outside of NLP with vocabularies comprising several 100 million words. Existing word2vec training systems are impractical for training such large vocabularies as they either require that the vectors of all vocabulary words be stored in the memory of a single server or suffer unacceptable training latency due to massive network data transfer. In this paper, we present a novel distributed, parallel training system that enables unprecedented practical training of vectors for vocabularies with several 100 million words on a shared cluster of commodity servers, using far less network traffic than the existing solutions. We evaluate the proposed system on a benchmark dataset, showing that the quality of vectors does not degrade relative to non-distributed training. Finally, for several quarters, the system has been deployed for the purpose of matching queries to ads in Gemini, the sponsored search advertising platform at Yahoo, resulting in significant improvement of business metrics.

* 10 pages, 2 figures 
Viaarxiv icon