Top-3 video-to-text retrieval results on CityFlow-NL dataset.

Top-3 video-to-text retrieval results on CityFlow-NL dataset.

<p>The four images from left to right represent snapshots of the vehicle trajectory over time, corresponding to the text description.</p>

Saved in:

Bibliographic Details
Main Author:	Changhao Zhang (547149) (author)
Other Authors:	Zhandong Liu (516336) (author), Ke Li (106849) (author), Yong Li (15029) (author), Xiangwei Qi (22032822) (author), Nan Ding (710349) (author)
Published:	2025
Subjects:	Ecology Science Policy Biological Sciences not elsewhere classified Information Systems not elsewhere classified test data set significantly enhanced image retrieving tracked vehicles natural language descriptions mean reciprocal ranking eliminate erroneous information camera surveillance scenarios video retrieval capabilities modal vehicle retrieval modal retrieval framework matching control system div >< p mvr system integrates view retrieval system designed mvr system utilizes clip traffic environments th </ recent advances ranked result processing techniques previous top paper introduces method achieves feature extraction contrastive learning based attributes
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Vehicle natural language description lables from CityFlow-NL dataset.
by: Changhao Zhang (547149)
Published: (2025)

Different video frames and natural language (NL) descriptions of the same vehicle are included in the CityFlow-NL training set.
by: Changhao Zhang (547149)
Published: (2025)

Examples of video frame images extracted from the Cityflow-nl dataset.
by: Changhao Zhang (547149)
Published: (2025)

Leaderboard for the tracked vehicle retrieval challenge using natural language descriptions.
by: Changhao Zhang (547149)
Published: (2025)

Ablation study analysis of our MVR method. MRR_I: Improvement in MRR, F_MRR: Final MRR Value.
by: Changhao Zhang (547149)
Published: (2025)

The example of control match system.
by: Changhao Zhang (547149)
Published: (2025)

Example of a vehicle motion module.
by: Changhao Zhang (547149)
Published: (2025)

The core architecture of our video recognition module involves different processing steps for visual and textual data.
by: Changhao Zhang (547149)
Published: (2025)

Overview of our proposed MVR framework.
by: Changhao Zhang (547149)
Published: (2025)

Operational mechanism diagram of deep reinforcement learning retrieval optimization module, based on the user interaction retrieval strategy optimization process, encodes the user query vector, historical interaction record and knowledge graph subgraph representation into state space, designs reward function, and trains the policy network through the proximal policy optimization algorithm (PPO) to optimize the retrieval strategy.
by: Yali Chen (24494)
Published: (2025)

Heatmap of the probability distribution of retrieval result ranking positions for MDKG-RL and Baseline models on the ICDAR 2023 dataset.
by: Yali Chen (24494)
Published: (2025)

Dynamic changes in reward values and retrieval accuracy over training iterations during deep reinforcement learning (DRL) training.
by: Yali Chen (24494)
Published: (2025)

Schematic diagram of the overall architecture of the MDKG-RL model, showing the process of multimodal archival data processing, knowledge graph construction and retrieval optimization.
by: Yali Chen (24494)
Published: (2025)

The working principle diagram of the multimodal Transformer feature extraction module, presenting the feature extraction and fusion process of text, image, and audio data, the specific steps of feature extraction of text data through the BERT model, image data with the help of Vision Transformer (ViT), and audio data with Audio Transformer, and finally the process of realizing multimodal feature fusion through the joint attention mechanism.
by: Yali Chen (24494)
Published: (2025)

Ablation study results of MDKG-RL model on ICDAR 2023 and AIDA corpus datasets: Comparison of performance metrics with component removal.
by: Yali Chen (24494)
Published: (2025)

Statistical significance of performance improvements between MDKG-RL and BERT-GNN models across multiple metrics.
by: Yali Chen (24494)
Published: (2025)

Comparative performance of different models on ICDAR 2023 and AIDA corpus datasets based on MRR, NDCG, , and ELA.
by: Yali Chen (24494)
Published: (2025)

Details of MDKG-RL model performance evaluation metrics.
by: Yali Chen (24494)
Published: (2025)

Experimental environment configuration details.
by: Yali Chen (24494)
Published: (2025)

Details of public datasets used in the experiment (ICDAR 2023 & AIDA Corpus).
by: Yali Chen (24494)
Published: (2025)

Confusion matrix showing the entity linking error distribution for core entities, long-tail entities, cross-modal ambiguity, events, locations, and organizations by the MDKG-RL model on the AIDA Corpus dataset.
by: Yali Chen (24494)
Published: (2025)

Boxplot comparing the response time distribution of MDKG-RL, BERT-GNN, and Baseline models on ICDAR 2023 and AIDA Corpus datasets.
by: Yali Chen (24494)
Published: (2025)

MDKG-RL model component ablation experiment performance comparison (ICDAR 2023 vs AIDA Corpus).
by: Yali Chen (24494)
Published: (2025)

Performance comparison of different models on ICDAR 2023 and AIDA Corpus datasets (MRR, NDCG, response time, entity linking accuracy).
by: Yali Chen (24494)
Published: (2025)

Schematic diagram of the construction and reasoning of the graph neural network and knowledge graph fusion module, covering the entity alignment in graph construction (mapping multimodal entity representations to a unified space based on the TransE model), relational reasoning (aggregating neighbor node features using the GraphSAGE model), and the process of logical rule injection and external knowledge fusion (through the SWRL rule engine and access to the general knowledge base).
by: Yali Chen (24494)
Published: (2025)

(a) ALOT Average Retrieval Precision (%). (b) ALOT Average Retrieval Recall (%).
by: Aiza Shabir (20896271)
Published: (2025)

(a) Tropical-Fruits Average Retrieval Precision (%). (b). Tropical-Fruits Average Retrieval Recall (%).
by: Aiza Shabir (20896271)
Published: (2025)

Cifar-10 Database Average Retrieval Recall (%).
by: Aiza Shabir (20896271)
Published: (2025)

Cifar-10 Database Average Retrieval Precision (%).
by: Aiza Shabir (20896271)
Published: (2025)

<b>Nestling retrieval behavior in two bunting hosts of the common cuckoo</b>
by: Yuhan Zhang (15426216)
Published: (2024)

African Market OS- MVR API Python SDK
by: Farouk Mark Mukiibi (22233445)
Published: (2025)

Example of moment retrieval from large-scale video collections.
by: Lingwen Meng (8968106)
Published: (2025)

SCOLIA25-Lesavourey_Hubert.pdf
by: International Workshop on Scholarly Information Access (21153161)
Published: (2025)

Evaluating and Improving Light Absorption Retrievals of Black Carbon Using In Situ Polar Nephelometry
by: Qizhi Xu (1729057)
Published: (2025)

Retrieval accuracy.
by: Xin-Yu Zhang (32378)
Published: (2024)

Retrieved
by: Retrieved Retrieved (20908057)
Published: (2025)

Retrieval computation cost.
by: Xin-Yu Zhang (32378)
Published: (2024)

Experimental results of image-text retrieval on ECCV Caption.
by: Ran Jin (726426)
Published: (2025)

Vocabulary intervention: Retrieval-based practice (Gordon et al., 2025)
by: Katherine R. Gordon (11525680)
Published: (2025)

SCOLIA25-Karl_Scherp.pdf
by: International Workshop on Scholarly Information Access (21153161)
Published: (2025)

Cannot write session to /tmp/vufind_sessions/sess_6ql1msdlrkgggbstatulvs28sn