Official pytorch repository for "QD-DETR : Query-Dependent Video Representation for Moment Retrieval and Highlight Detection" (CVPR 2023 Paper)

Official pytorch repository for CG-DETR "Correlation-guided Query-Dependency Calibration in Video Representation Learning for Temporal Grounding"

Official implementation of "NeighborRetr: Balancing Hub Centrality in Cross-Modal Retrieval (CVPR 2025)"

The code for the paper "Hybrid Contrastive Quantization for Efficient Cross-View Video Retrieval" (WWW'22, Oral).

[TIP25] Code for "Text-Video Retrieval with Global-Local Semantic Consistent Learning"

Coarse-to-Fine Grained Text-based Video-moment Retrieval pipeline utilizing T-MASS and MESM models for efficient multi-stage text-video alignment.

Dataviz AI is an AI powered web application that enables users to generate animated infographic videos based on input Data ,files. This MVP leverages the gen ai models for video content and incorporates advanced natural language processing (NLP) techniques, including LangChain and stable diffusion techniques, to analyze and create visual impact.

The code for the paper "GMMFormer: Gaussian-Mixture-Model Based Transformer for Efficient Partially Relevant Video Retrieval" (AAAI'24)

[ICASSP 2024 Oral] WAVER: Writing-Style Agnostic Text-Video Retrieval Via Distilling Vision-Language Models Through Open-Vocabulary Knowledge

The code for the paper "HLFormer: Enhancing Partially Relevant Video Retrieval with Hyperbolic Learning" (ICCV'25).

Official implementation of "Diffusion-Inspired Truncated Sampler for Text-Video Retrieval (NeurIPS 2024)"

Q2E: Query-to-Event Decomposition for Zero-Shot Multilingual Text-to-Video Retrieval