Author name cluster

Anil Sharma

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

2 author rows

AAAI Conference 2026 Conference Paper

ContextGraph: Lifelog Intelligence Framework for Contextual Subgraph Evolution

Anil Sharma
Gunturi Venkata Sai Phani Kiran
Jayesh Rajkumar Vachhani
Sourabh Vasant Gothe
Ayon Chattopadhyay
Yashwant Saini
Parameswaranath Vadackupurath Mani
Barath Raj Kandur Raja

Lifelogging involves the continuous and comprehensive recording of a user’s daily activities, behaviors, and interactions, offering valuable insights for personalized healthcare, event retrieval, and lifestyle analysis. However, extracting meaningful patterns from lifelog data requires models to capture deeper temporal contexts beyond simple retrieval. To address this, we introduce ContextGraph, a lifelog intelligence framework that models lifelogs as a Temporal Knowledge Graph (TKG) to reason about the user’s evolving life patterns over time. ContextGraph computes Day Context Embeddings (DCE) to encode the temporal spread and social scene context of user's daily behavior. Then a novel Lens module extracts semantically meaningful subgraph snapshots around an anchor node in the TKG, representing specific personal contexts in the user’s life. The Lens module also computes an evolution signature for each subgraph, indicating whether it is growing, decaying, or remaining static. By analyzing these evolution signatures, ContextGraph provides actionable insights into the user’s lifelogs such as stable routines, behavioral drifts, or lifestyle changes. Our experiments showcase DCE's versatility, outperforming baselines in graph/node classification and reasoning on the Enzyme and DBLP datasets.

PDF Details DOI

IJCAI Conference 2019 Conference Paper

Intelligent Querying in Camera Networks for Efficient Target Tracking

Anil Sharma

Visual analytics applications often rely on target tracking across a network of cameras for inference and prediction. A network of cameras generates immense amount of video data and processing it for tracking a target is highly computationally expensive. Related works typically use data association and visual re-identification techniques to match target templates across multiple cameras. In this thesis, I propose to formulate this scheduling problem as a Markov Decision Process (MDP) and present a reinforcement learning based solution to schedule cameras by selecting one where the target is most likely to appear next. The proposed approach can be learned directly from data and doesn't require any information of the camera network topology. NLPR MCT and DukeMTMC datasets are used to show that the proposed policy significantly reduces the number of frames to be processed for tracking and identifies the camera schedule with high accuracy as compared to the related approaches. Finally, I will be formulating an end-to-end pipeline for target tracking that will learn a policy to find the camera schedule and to track the target in the individual camera frames of the schedule.

PDF Details

RLDM Conference 2019 Conference Abstract

Reinforcement Learning Based Querying in a Network of Cameras

Anil Sharma
Saket Anand
Sanjit K

Surveillance camera networks are a useful monitoring infrastructure that can be used for various visual analytics applications, where high-level inferences and predictions could be made based on target tracking across the network. Most multi-camera tracking works focus on re-identification problems and trajectory association problems. However, as camera networks grow in size, the volume of data generated is humongous, and scalable processing of this data is imperative for deploying practical solutions. In this paper, we address the largely overlooked problem of scheduling cameras for processing by selecting one where the target is most likely to appear next. The inter-camera handover can then be performed on the selected cameras via re-identification or another target association technique. We model this scheduling problem using reinforcement learning and learn the camera selection policy using Q-learning. We do not assume the knowledge of the camera network topology but we observe that the resulting policy implicitly learns it. We will also show that such a policy can be learnt directly from data. We evaluate our approach using NLPR MCT dataset, which is a real multi-camera multi-target tracking benchmark and show that the proposed policy substantially reduces the number of frames required to be processed at the cost of a small reduction in recall.

PDF Details

ICAPS Conference 2019 Conference Paper

Reinforcement Learning Based Querying in Camera Networks for Efficient Target Tracking

Anil Sharma
Saket Anand
Sanjit K. Kaul

Surveillance camera networks are a useful monitoring infrastructure that can be used for various visual analytics applications, where high-level inferences and predictions could be made based on target tracking across the network. Most multi-camera tracking works focus on re-identification problems and trajectory association problems. However, as camera networks grow in size, the volume of data generated is humongous, and scalable processing of this data is imperative for deploying practical solutions. In this paper, we address the largely overlooked problem of scheduling cameras for processing by selecting one where the target is most likely to appear next. The inter-camera handover can then be performed on the selected cameras via re-identification or another target association technique. We model this scheduling problem using reinforcement learning and learn the camera selection policy using Q-learning. We do not assume the knowledge of the camera network topology but we observe that the resulting policy implicitly learns it. We evaluate our approach using NLPR MCT dataset, which is a real multi-camera multi-target tracking benchmark and show that the proposed policy substantially reduces the number of frames required to be processed at the cost of a small reduction in recall.

Details

AAMAS Conference 2018 Conference Paper

Foresee: Attentive Future Projections of Chaotic Road Environments

Anil Sharma
Arun Balaji Buduru

In this paper, we train a recurrent neural network to learn dynamics of a chaotic road environment and to project the future of the environment on an image. Future projection can be used to anticipate an unseen environment for autonomous driving. Road environment is highly dynamic and complex due to the interaction among traffic participants such as vehicles and pedestrians. Even in such a complex environment, a human driver can easily anticipate the environment and is efficacious to drive safely on the chaotic roads. Proliferation in deep learning research has shown the efficacy of neural networks in learning this kind of human behavior. In the same direction, we investigate recurrent neural networks to understand the road environment. We propose Foresee, a unidirectional gated recurrent units (GRUs) network with attention to project future of the environment in the form of images. We have collected several videos on Delhi roads consisting of various traffic participants, background and infrastructure differences (like 3D pedestrian crossing) at various times on various days. We show that our proposed model performs better than state of the art methods (prednet [9], Enc. Dec. LSTM [15]).

PDF