Manish Gupta
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Manish Gupta has a total of 202 co-authors. Here are the top co-authors by number of shared publications:
- Vasudeva Varma
IIIT Hyderabad
11 shared publications Vasudeva Varma
IIIT-Hyderabad India
7 shared publications- Anand Mishra
Indian Institute of Technology Jodhpur
6 shared publications - Puneet Agrawal
Microsoft
6 shared publications - Subba Reddy Oota
Technical University of Berlin
6 shared publications - Subba Reddy Oota
Technische Universität Berlin Germany
5 shared publications
Latest Publications
- 24 September 2026
- Published by Elsevier in Computer Vision and Image Understanding
- Vol. 273
Moment alignment transformer for video-to-video moment retrieval
- 24 September 2026
- Published by Elsevier in Computer Vision and Image Understanding
- Vol. 273
Moment alignment transformer for video-to-video moment retrieval
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1336-1346
DocQAC: Adaptive Trie-Guided Decoding for Effective In-Document Query Auto-Completion
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1336-1346
Open AccessDocQAC: Adaptive Trie-Guided Decoding for Effective In-Document Query Auto-Completion
- 25 March 2026
- Published by Springer Nature
- p. 352-367
SUMMIR: A Hallucination-Aware Framework for Ranking Sports Insights from LLMs
- 25 March 2026
- Published by Springer Nature
- p. 352-367
SUMMIR: A Hallucination-Aware Framework for Ranking Sports Insights from LLMs
- Open Access
- 14 March 2026
- Published by Elsevier in SSRN Electronic Journal
Moment Alignment Transformer for Video-to-Video Moment Retrieval
Video-to-video moment retrieval (Vid2VidMR) is the task of localizing unseen events or moments in a target video using a query video. This task is challenging due to the need for semantic frame-level alignment and modeling complex dependencies between query and target videos. To address this, we introduce MATR (Moment Alignment TRansformer), a transformer-based model that captures semantic context and temporal detail for precise moment localization. MATR conditions target video representations on query features through dual-stage sequence alignment, encoding the necessary correlations and dependencies. These representations guide foreground/background classification and boundary prediction heads to identify moments in the target video that semantically match the query. To provide strong task-specific initialization, we further propose a self-supervised pre-training objective where the model learns to localize random clips within videos. Extensive experiments show that MATR achieves absolute gains of 15.4% in R@1 and 11.4% in mIoU over state-of-the-art methods on the ActivityNet-VRL dataset, and 16.4% in R@1 and 16.3% in mIoU on our newly proposed SportsMoments dataset. Code is available at: https://github.com/vl2g/MATR.
- 14 March 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessMoment Alignment Transformer for Video-to-Video Moment Retrieval
Video-to-video moment retrieval (Vid2VidMR) is the task of localizing unseen events or moments in a target video using a query video. This task is challenging due to the need for semantic frame-level alignment and modeling complex dependencies between query and target videos. To address this, we introduce MATR (Moment Alignment TRansformer), a transformer-based model that captures semantic context and temporal detail for precise moment localization. MATR conditions target video representations on query features through dual-stage sequence alignment, encoding the necessary correlations and dependencies. These representations guide foreground/background classification and boundary prediction heads to identify moments in the target video that semantically match the query. To provide strong task-specific initialization, we further propose a self-supervised pre-training objective where the model learns to localize random clips within videos. Extensive experiments show that MATR achieves absolute gains of 15.4% in R@1 and 11.4% in mIoU over state-of-the-art methods on the ActivityNet-VRL dataset, and 16.4% in R@1 and 16.3% in mIoU on our newly proposed SportsMoments dataset. Code is available at: https://github.com/vl2g/MATR.
- Open Access
A Deep Multi-Modal Method for Patient Wound Healing Assessment
Hospitalization of patients is one of the major factors for high wound care costs. Most patients do not acquire a wound which needs immediate hospitalization. However, due to factors such as delay in treatment, patient's non-compliance or existing co-morbid conditions, an injury can deteriorate and ultimately lead to patient hospitalization. In this paper, we propose a deep multi-modal method to predict the patient's risk of hospitalization. Our goal is to predict the risk confidently by collectively using the wound variables and wound images of the patient. Existing works in this domain have mainly focused on healing trajectories based on distinct wound types. We developed a transfer learning-based wound assessment solution, which can predict both wound variables from wound images and their healing trajectories, which is our primary contribution. We argue that the development of a novel model can help in early detection of the complexities in the wound, which might affect the healing process and also reduce the time spent by a clinician to diagnose the wound.
Open AccessA Deep Multi-Modal Method for Patient Wound Healing Assessment
Hospitalization of patients is one of the major factors for high wound care costs. Most patients do not acquire a wound which needs immediate hospitalization. However, due to factors such as delay in treatment, patient's non-compliance or existing co-morbid conditions, an injury can deteriorate and ultimately lead to patient hospitalization. In this paper, we propose a deep multi-modal method to predict the patient's risk of hospitalization. Our goal is to predict the risk confidently by collectively using the wound variables and wound images of the patient. Existing works in this domain have mainly focused on healing trajectories based on distinct wound types. We developed a transfer learning-based wound assessment solution, which can predict both wound variables from wound images and their healing trajectories, which is our primary contribution. We argue that the development of a novel model can help in early detection of the complexities in the wound, which might affect the healing process and also reduce the time spent by a clinician to diagnose the wound.
- Open Access
Router-Suggest: Dynamic Routing for Multimodal Auto-Completion in Visually-Grounded Dialogs
Real-time multimodal auto-completion is essential for digital assistants, chatbots, design tools, and healthcare consultations, where user inputs rely on shared visual context. We introduce Multimodal Auto-Completion (MAC), a task that predicts upcoming characters in live chats using partially typed text and visual cues. Unlike traditional text-only auto-completion (TAC), MAC grounds predictions in multimodal context to better capture user intent. To enable this task, we adapt MMDialog and ImageChat to create benchmark datasets. We evaluate leading vision-language models (VLMs) against strong textual baselines, highlighting trade-offs in accuracy and efficiency. We present Router-Suggest, a router framework that dynamically selects between textual models and VLMs based on dialog context, along with a lightweight variant for resource-constrained environments. Router-Suggest achieves a 2.3x to 10x speedup over the best-performing VLM. A user study shows that VLMs significantly excel over textual models on user satisfaction, notably saving user typing effort and improving the quality of completions in multi-turn conversations. These findings underscore the need for multimodal context in auto-completions, leading to smarter, user-aware assistants.
Open AccessRouter-Suggest: Dynamic Routing for Multimodal Auto-Completion in Visually-Grounded Dialogs
Real-time multimodal auto-completion is essential for digital assistants, chatbots, design tools, and healthcare consultations, where user inputs rely on shared visual context. We introduce Multimodal Auto-Completion (MAC), a task that predicts upcoming characters in live chats using partially typed text and visual cues. Unlike traditional text-only auto-completion (TAC), MAC grounds predictions in multimodal context to better capture user intent. To enable this task, we adapt MMDialog and ImageChat to create benchmark datasets. We evaluate leading vision-language models (VLMs) against strong textual baselines, highlighting trade-offs in accuracy and efficiency. We present Router-Suggest, a router framework that dynamically selects between textual models and VLMs based on dialog context, along with a lightweight variant for resource-constrained environments. Router-Suggest achieves a 2.3x to 10x speedup over the best-performing VLM. A user study shows that VLMs significantly excel over textual models on user satisfaction, notably saving user typing effort and improving the quality of completions in multi-turn conversations. These findings underscore the need for multimodal context in auto-completions, leading to smarter, user-aware assistants.
- 2 January 2026
- Published by Springer Nature
- p. 1-11
Assessing Performance of Large Language Models in Generating Local and Trending Query Auto-completions
- 2 January 2026
- Published by Springer Nature
- p. 1-11
Assessing Performance of Large Language Models in Generating Local and Trending Query Auto-completions
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 5634-5641
When Words Can't Capture It All: Towards Video-Based User Complaint Text Generation with Multimodal Video Complaint Dataset
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 5634-5641
Open AccessWhen Words Can't Capture It All: Towards Video-Based User Complaint Text Generation with Multimodal Video Complaint Dataset
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 5551-5558
EnhanceMyPrompt: Rewriting Chat Queries for Effective Response Generation from LLMs
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 5551-5558
Open AccessEnhanceMyPrompt: Rewriting Chat Queries for Effective Response Generation from LLMs
- Open Access
TripTide: A Benchmark for Adaptive Travel Planning under Disruptions
Recent efforts like TripCraft and TravelPlanner have advanced the use of Large Language Models ( LLMs) for personalized, constraint aware travel itinerary generation. Yet, real travel often faces disruptions. To address this, we present TripTide, the first benchmark evaluating LLM's ability to revise itineraries under realistic disruptions. TripTide models key dimensions such as disruption severity and traveler tolerance, enabling nuanced assessment of LLM adaptability to events like flight cancellations, weather closures, or overbooked attractions. We conduct a threefold evaluation. First, we introduce automatic metrics including Preservation of Intent (how well the revised plan maintains feasibility and goals), Responsiveness (promptness and appropriateness of disruption handling), and Adaptability (semantic, spatial, and sequential divergence between original and revised plans). Second, we apply an LLM-as-a-judge approach to automatically assess revision quality. Third, we perform manual expert evaluation to verify whether revisions preserve semantic, spatial, sequential, and responsive aspects. Our experiments show that LLMs maintain strong sequential consistency and semantic stability, while spatial deviations are larger for shorter trips but decrease with longer ones, indicating that extended plans encourage better geographic coherence. However, disruption-handling ability declines as plan length increases, highlighting limits in LLM robustness. TripTide establishes a benchmark for evaluating adaptability, personalization, and resilience in LLM-based travel planning under real-world uncertainty.
Open AccessTripTide: A Benchmark for Adaptive Travel Planning under Disruptions
Recent efforts like TripCraft and TravelPlanner have advanced the use of Large Language Models ( LLMs) for personalized, constraint aware travel itinerary generation. Yet, real travel often faces disruptions. To address this, we present TripTide, the first benchmark evaluating LLM's ability to revise itineraries under realistic disruptions. TripTide models key dimensions such as disruption severity and traveler tolerance, enabling nuanced assessment of LLM adaptability to events like flight cancellations, weather closures, or overbooked attractions. We conduct a threefold evaluation. First, we introduce automatic metrics including Preservation of Intent (how well the revised plan maintains feasibility and goals), Responsiveness (promptness and appropriateness of disruption handling), and Adaptability (semantic, spatial, and sequential divergence between original and revised plans). Second, we apply an LLM-as-a-judge approach to automatically assess revision quality. Third, we perform manual expert evaluation to verify whether revisions preserve semantic, spatial, sequential, and responsive aspects. Our experiments show that LLMs maintain strong sequential consistency and semantic stability, while spatial deviations are larger for shorter trips but decrease with longer ones, indicating that extended plans encourage better geographic coherence. However, disruption-handling ability declines as plan length increases, highlighting limits in LLM robustness. TripTide establishes a benchmark for evaluating adaptability, personalization, and resilience in LLM-based travel planning under real-world uncertainty.