Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks93 from public data
- Learning 2D Temporal Adjacent Networks for Moment Localization with Natural Language640
A Temporal Adjacent Network (2D-TAN) is proposed, a single-shot framework for moment localization that is capable of encoding the adjacent temporal relation, while learning discriminative features for matching video moments with referring expressions.
- 430
- Part-Aware Prototype Network for Few-Shot Semantic Segmentation424
A novel few-shot semantic segmentation framework based on the prototype representation, capable of capturing diverse and fine-grained object features, and a novel graph neural network model to generate and enhance the proposed part-aware prototypes based on labeled and unlabeled images.
- InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model397
Experimental results demonstrate the superiority of InternLM-XComposer2 based on InternLM2-7B in producing high-quality long-text multi-modal content and its exceptional vision-language understanding performance across various benchmarks, where it not only significantly outperforms existing multimodal models but also matches or even surpasses GPT-4V and Gemini Pro in certain assessments.
- Distribution Alignment: A Unified Framework for Long-tail Visual Recognition376
This work develops an adaptive calibration function that enables us to adjust the classification scores for each data point in the two-stage learning to balance the class prior, which provides a flexible and unified solution to diverse scenarios in visual recognition tasks.
- InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition361
This work proposes InternLM-XComposer, a vision-language large model that enables advanced image-text comprehension and composition that achieves competitive text-image composition scores compared to public solutions, including GPT4-V and GPT3.5.
- 323
- 314
- 309
- Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generation282
This work introduces a novel confidence-aware bipartite graph neural network with adaptive message propagation mechanism for unbiased scene graph generation and proposes an efficient bi-level data resampling strategy to alleviate the imbalanced data distribution problem in training the authors' graph network.
- InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output216
A versatile large-vision language model that supports long-contextual input and output, InternLM-XComposer-2.5 excels in various text-image comprehension and composition applications, achieving GPT-4V level capabilities with merely 7B LLM backend.
- Boundary Proposal Network for Two-stage Natural Language Video Localization196
A novel Boundary Proposal Network (BPNet) is proposed, a universal two-stage framework that gets rid of the issues mentioned above and outperforms the state-of-the-art NLVL methods.
- SGTR: End-to-end Scene Graph Generation with Transformer193
A transformer-based end-to-end framework that first generates the entity and predicate proposal set, followed by inferring directed edges to form the relation triplets, and a new entity-aware predicate representation based on a structural predicate generator that leverages the compositional property of relationships is developed.
- 193
- Latent-Shift: Latent Diffusion with Temporal Shift for Efficient Text-to-Video Generation152
This work proposes a parameter-free temporal shift module that can leverage the spatial U-Net as is for video generation and achieves comparable or better results while being significantly more efficient.
- The Devil is in the Labels: Noisy Label Correction for Robust Scene Graph Generation113
This paper proposes a novel model-agnostic NoIsy label CorrEction strategy for SGG: NICE, which can not only detect noisy samples but also reassign more high-quality predicate labels to them.
- T-Eval: Evaluating the Tool Utilization Capability of Large Language Models Step by Step112
T-Eval provides a more fine-grained analysis of the capabilities of LLMs, providing a new perspective in LLM evaluation on tool-utilization ability, and comprehensively decompose the tool utilization into multiple sub- processes, including instruction following, planning, reasoning, retrieval, understanding, and review.
- Dynamic Context Correspondence Network for Semantic Alignment98
This paper proposes a context-aware semantic representation that incorporates spatial layout for robust matching against local ambiguities and develops a novel dynamic fusion strategy based on attention mechanism to weave the advantages of both local and context features by integrating semantic cues from multiple scales.
- LawBench: Benchmarking Legal Knowledge of Large Language Models89
Using LawBench, the first evaluation benchmark composed of 20 tasks aimed to assess the ability of Large Language Models (LLMs) to perform Chinese legal-related tasks, this work presents a comprehensive evaluation of 21 popular LLMs and the first comparative analysis of the empirical results.
- From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Models81
A new open-vocabulary SGG framework based on sequence generation that leverages vision-language pre-trained models (VLM) by incorporating an image-to-graph generation paradigm and seamlessly integrate explicit relational modeling for enhancing the VL tasks.
- Exploiting Temporal Relationships in Video Moment Localization with Natural Language78
A novel Temporal Compositional Modular Network (TCMN) where a tree attention network first automatically decomposes a sentence into three descriptions with respect to the main event, context event and temporal signal is proposed.
- Multi-Scale 2D Temporal Adjacency Networks for Moment Localization With Natural Language75
A Multi-Scale Temporal Adjacency Network (MS-2D-TAN), a single-shot framework for moment localization capable of encoding the adjacent temporal contexts at each scale, while learning discriminative features for matching video moments with referring expressions is proposed.
- A Dual Attention Network with Semantic Embedding for Few-Shot Learning70
This work proposes a novel meta-learning method for few-shot classification based on two simple attention mechanisms: one is a spatial attention to localize relevant object regions and the other is a task attention to select similar training data for label prediction.
- NeedleBench: Evaluating LLM Retrieval and Reasoning Across Varying Information Densities67
The NeedleBench framework is used to assess how well the leading open-source models can identify key information relevant to the question and apply that information to reasoning in bilingual long texts, and the Ancestral Trace Challenge (ATC) is proposed to mimic the complexity of logical reasoning challenges that are likely to be present in real-world long-context tasks.
- 65
- Cross Modality Bias in Visual Question Answering: A Causal View With Possible Worlds VQA63
This is the first work to reduce biases resulting from confounding effects of vision and language in VQA, leveraging causal explain-away relations and outperforms the state-of-the-art methods in VQA-CP v2 datasets.
- Learning Implicit Temporal Alignment for Few-shot Video Classification58
This work introduces an implicit temporal alignment for a video pair, capable of estimating the similarity between them in an accurate and robust manner, and designs an effective context encoding module to incorporate spatial and feature channel context, resulting in better modeling of intra-class variations.
- Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning53
A token-level reward model is applied to sample important tokens in reasoning trajectories for learning and theoretically proves that behavior cloning on positive trajectories from best-of-N (BoN) sampling is sufficient to learn the KL-regularized optimal policy in binary feedback environments.
- 51
- Improving Pixel-based MIM by Reducing Wasted Modeling Capability49
This paper is the first to systematically investigate multilevel feature fusion for isotropic architectures like the standard Vision Transformer (ViT) and is the first to systematically investigate multilevel feature fusion for isotropic architectures like the standard Vision Transformer (ViT).
- HelloBench: Evaluating Long Text Generation Capabilities of Large Language Models48
The Hierarchical Long Text Generation Benchmark (HelloBench), a comprehensive, in-the-wild, and open-ended benchmark to evaluate LLMs' performance in generating long text and the proposed HelloEval, a human-aligned evaluation method that significantly reduces the time and effort required for human evaluation while maintaining a high correlation with human evaluation.
- PixMIM: Rethinking Pixel Reconstruction in Masked Image Modeling47
A remarkably simple and effective method that entails filtering the high-frequency components from the reconstruction target to de-emphasize the network's focus on texture-rich details and adopting a conservative data transform strategy to alleviate the problem of missing foreground in MIM training is proposed.
- An EM Framework for Online Incremental Learning of Semantic Segmentation45
A unified learning strategy based on the Expectation-Maximization (EM) framework, which integrates an iterative relabeling strategy that fills in the missing labels and a rehearsal-based incremental learning step that balances the stability-plasticity of the model.
- Dynamic Grained Encoder for Vision Transformers44
A Dynamic Grained Encoder for vision transformers is proposed, which can adaptively assign a suitable number of queries to each spatial region and achieves a fine-grained representation in discriminative regions while keeping high efficiency.
- Machine-Learning-Enabled Framework in Engineering Plastics Discovery: A Case Study of Designing Polyimides with Desired Glass-Transition Temperature39
This work collected a dataset of 878 polyimides (PI), one of the best engineering plastics, with experimentally measured glass-transition temperature (Tg) values, and developed a rapid and accurate ML approach to design PI candidates with the desired Tg value, which could offer a scalable and adaptable framework in future engineer plastics innovation.
- 38
- RIFormer: Keep Your Vision Backbone Effective But Removing Token Mixer33
This paper develops an RepIdentityFormer base on the re-parameterizing idea, and explores the improved learning paradigm to break the limitation of simple token mixer free backbone, and summarizes the empirical practice into 5 guidelines.
- 33
- Content-based Analysis of the Cultural Differences between TikTok and Douyin30
By comparing the distributional results of TikTok and Douyin, a wealth of similarity and contrast is uncovered between the two closely related video social media platforms along the content dimensions of object quantity, object categories, and human action categories.
- Video-aided Unsupervised Grammar Induction29
This paper investigates video-aided grammar induction, which learns a constituency parser from both unlabeled text and its corresponding video, and proposes a Multi-Modal Compound PCFG model (MMC-PCFG), which outperforms each individual modality and previous state-of-the-art systems on three benchmarks.
- 26
- 25
- 24
- Instance-wise or Class-wise? A Tale of Neighbor Shapley for Concept-based Explanation24
This paper proposes a novel COncept-based NEighbor Shapley approach (dubbed as CONE-SHAP) to evaluate the importance of each concept by considering its physical and semantic neighbors, and interpret model knowledge with both instance-wise and class-wise explanations.
- Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations20
It is found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance, which indicates that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy.
- Transformer with Bidirectional Decoder for Speech Recognition20
This work introduces a bidirectional speech transformer to utilize the different directional contexts simultaneously, and uses the introduced biddirectional beam search method to generate left-to-right candidates but also right- to-left candidates and determine the best hypothesis by the score.
- Explorations of skeleton features for LSTM-based action recognition17
This work utilizes a universal spatial model perpendicular to the RNN model enhancement, and proposes two simple geometric features, inspired by previous work, which outperform other methods and achieve state-of-art results on two datasets.
- Rethinking the Evaluation of Unbiased Scene Graph Generation15
This paper refine mR@K and propose two complementary evaluation metrics for unbiased SGG: Independent Mean Recall (MR) and weighted IMR (wIMR) which are designed by considering the category independence and diversity of composable relation triplets, respectively.
- 14
- 14
- A UAV perspective based lightweight target detection and tracking algorithm for intelligent transportation12
A YOLO-LMP and NGCTrack-based target detection and tracking algorithm to addressVehicle detection and tracking from a UAV perspective often encounters omission and misdetection due to the small targets, complex scenes and target occlusion.
- 12
- FedSC: Provable Federated Self-supervised Learning with Spectral Contrastive Objective over Non-i.i.d. Data11
This work proposes a provable FedSSL algorithm, named FedSC, based on the spectral contrastive objective, which enables inter-client contrast of data samples in addition to intra-client contrast and contraction, resulting in improved quality of data representations.
- PS-FedGAN: An Efficient Federated Learning Framework Based on Partially Shared Generative Adversarial Networks For Data Privacy9
This work proposes a novel FL framework that requires only partial GAN model sharing and enhances the GAN releasing and training mechanism to address heterogeneous data distributions across clients and to strengthen privacy preservation at reduced communication cost, especially over wireless networks.
- Mi YouTube es Su YouTube? Analyzing the Cultures using YouTube Thumbnails of Popular Videos9
This study explores culture preferences among countries using the th thumbnail images of YouTube trending videos to demonstrate that discovering the culture preference through the thumbnails can be an effective mechanism for video social media analysis.
- 8
- Temporal Segment Transformer for Action Segmentation8
An attention based approach to denoise segment representations using attention between segment and frame representations, and also use inter-segment attention to capture temporal correlations between segments for joint segment relation modeling and denoising.
- Learning Referring Video Object Segmentation from Weak Annotation8
A new annotation scheme is proposed that reduces the annotation effort by 8 times, while providing sufficient supervision for RVOS, and a novel RVOS method is developed that exploits weak annotations effectively and achieves comparable or even superior performance to fully-supervised methods, without requiring dense masks.
- 7
- 7
- ATLAS: A High-Difficulty, Multidisciplinary Benchmark for Frontier Scientific Reasoning6
ATLAS (AGI-Oriented Testbed for Logical Application in Science) is introduced, a large-scale, high-difficulty, and cross-disciplinary evaluation suite composed of approximately 800 original problems that demonstrates ATLAS's effectiveness in differentiating their advanced scientific reasoning capabilities.
- Global Image Sentiment Transfer6
Both qualitative and quantitative evaluations demonstrate that the proposed sentiment transfer framework outperforms existing artistic and photo-realistic style transfer algorithms in producing satisfactory sentiment transfer results with fine and exact details.
- 5
- 5
- 3
- 3
- PFL-GAN: When Client Heterogeneity Meets Generative Models in Personalized Federated Learning3
This work proposes a novel GAN sharing and aggregation strategy for PFL that addresses the client heterogeneity in different scenarios and first learns the similarity among clients and then develops an weighted collaborative data aggregation.
- Unveiling Cross Modality Bias in Visual Question Answering: A Causal View with Possible Worlds VQA3
This work first model a confounding effect that causes language and vision bias simultaneously, then proposes a counterfactual inference to remove the influence of this effect, and concludes that the model trained in this strategy can concurrently and efficiently reduce vision and language bias.
- UFed-GAN: A Secure Federated Learning Framework with Constrained Computation and Unlabeled Data3
This work proposes a novel framework of UFed-GAN: Unsupervised Federated Generative Adversarial Network, which can capture user-side data distribution without local classification training and demonstrates the strong potential of U Fed-GAN in addressing limited computational resources and unlabeled data while preserving privacy.
- 3
- NeuroDesignScience: An fNIRS-Based System Designed to Help Pilots Sustain Attention During Transmeridian Flights3
A system to help pilots maintain attention on tasks over time to reduce air accidents is proposed and an experiment was designed to examine whether using this system could reduce pilots’ missed instructions when communicating with ground control.
- 3
- 2
- 2
- 2
- 2
- Efficient Multi-Worker Selection Based Distributed Swarm Learning via Analog Aggregation1
This paper proposes an over-the-air (OTA) analog aggregation method designed for the distributed swarm learning (DSL), termed DSL-OTA, aiming to enhance communication efficiency, enable effective cooperation, and ensure privacy preserving.
- Multi-Worker Selection based Distributed Swarm Learning for Edge IoT with Non-i.i.d. Data1
A new multi-worker selection design for DSL, termed M-DSL algorithm, which works effectively with distributed heterogeneous data, and guides effective selection of multiple works who make prominent contributions for global model updates.
- A digital speckle stereo matching algorithm based on epipolar line correction1
An estimation method of deformational iterative initial values of the first-order shape function in the stereo matching process is given through theoretical derivation, and the experimental results show that this method can complete the matching well under different inclined field of view.
- FoundaBench: Evaluating Chinese Fundamental Knowledge Capabilities of Large Language Models1
An extensive evaluation of 12 state-of-the-art LLMs using FoundaBench, employing both traditional assessment methods and the CircularEval protocol to mitigate potential biases in model responses reveals a significant disparity between models' reasoning and memory recall capabilities.
- 1
- Basic and Clinical Research Progress of Traditional Chinese Medicine in Treating Insomnia after Stroke–
This paper systematically reviews the basic and clinical research on TCM treatment of PSI at home and abroad in recent years and shows that TCM therapy is effective, not only relieving the clinical symptoms of PSI patients but also improving their quality of life.
- –
- –
- –
- Towards Efficient Federated Learning of Networked Mixture-of-Experts for Mobile Edge Computing–
This work introduces the Networked Mixture-of-Experts (NMoE) system, in which clients perform inference collaboratively by distributing tasks to suitable neighbors based on their expertise and aggregate the returned results.
- –
- –
- –
- –
- –
- –
- Research on News Neologisms Identifi cation with Long Term Extraction Technology–
The news neologisms identification technology can be used in such areas as English-Chinese translation, mobile software information push and so on.
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-14. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.