Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks22 from public data
- MuCAN: Multi-correspondence Aggregation Network for Video Super-Resolution185
This work proposes a temporal multi-correspondence aggregation strategy to leverage similar patches across frames, and a cross-scale nonlocal-cor correspondence aggregation scheme to explore self-similarity of images across scales.
- 58
- 32
- D3G: Exploring Gaussian Prior for Temporal Sentence Grounding with Glance Annotation26
This study investigates a recently proposed glance-supervised temporal sentence grounding task, which requires only single frame annotation (referred to as glance annotation) for each query and proposes a Dynamic Gaussian prior based Grounding framework with Glance annotation, which outperforms the state-of-the-art weakly supervised methods by a large margin and narrows the performance gap compared to fully supervised methods.
- 18
- 16
- AlphaEval: A Comprehensive and Efficient Evaluation Framework for Formula Alpha Mining14
AlphaEval is proposed, a unified, parallelizable, and backtest-free evaluation framework for automated alpha mining models that effectively identifies superior alphas compared to traditional single-metric screening approaches.
- VLMAE: Vision-Language Masked Autoencoder14
VLMAE employs visual generative learning, facilitating the model to acquire fine-grained and unbiased features, and achieves better performance in various vision-language downstream tasks, including visual question answering, image-text retrieval and visual grounding.
- MASS: Muli-agent simulation scaling for portfolio construction13
The Multi-Agent Scaling Simulation (MASS) is introduced, a novel framework that leverages multi-agent simulation for direct, end-to-end portfolio construction and demonstrates that as the number of agents increases exponentially, the aggregated decisions yield progressively higher excess returns.
- S2A: Scale-Attention-Aware Networks for Video Super-Resolution4
A novel SAA network is proposed, that is, Scale-and-Attention-Aware Networks, to apply different attention to different temporal-length streams, while further exploring both spatial and channel attention on separate streams with a newly proposed Criss-Cross Channel Attention Module (C3AM).
- 3
- CogniTrust: Cognitive Memory-Driven Verifiable Supervision for Robust Hashing1
Inspired by cognitive theories of human memory, a novel framework called CogniTrust is proposed that unifies verifiable supervision with a triadic memory model, allowing supervision to be refined through the joint consideration of spatial structure and semantic information.
- 1
- Exploiting Feature Diversity for Make-up Temporal Video Grounding1
This technical report presents the 3rd winning solution for MTVG, a new task introduced in the 4-th Person in Context (PIC) Challenge at ACM MM 2022, which aims at localizing the temporal boundary of the step in an untrimmed video based on a textual description via exploiting feature diversities.
- UA-DRN: Unbiased Aggregation of Deep Neural Networks for Regression Ensemble.1
The proposed framework, called the Unbiased Aggregation of Deep Regression Network (UA-DRN), contributes both in the training phase and the deploy phase and can consistently improve the regression performance in term of different quantitative metrics.
- –
- MindLoom: Composing Thought Modes for Frontier-Level Reasoning Data Synthesis–
This work proposes MindLoom, a framework for synthesizing frontier-level reasoning data through compositional thought mode engineering and evaluates MindLoom on nine benchmarks covering five STEM disciplines and four mathematical reasoning tasks across multiple model families and sizes.
- RSPO: Reward-Swap Policy Optimization for Multi-Turn LLM Agents–
Reinforcement learning holds significant potential for training large language models to handle multi-turn interactive tasks, but directly training with outcome rewards often results in slow convergence due to the sparsity of signals and the lack of fine-grained feedback.
- –
- Unified and Dynamic Graph for Temporal Character Grouping in Long Videos–
This paper presents a unified and dynamic graph (UniDG) framework for temporal character grouping by creating a unified representation network that learns representations of multiple modalities within the same space and still preserves the modality's uniqueness simultaneously.
- –
- Self-attentive Pyramid Network for Single Image De-raining–
A deep self-attentive pyramid network (SAPN) is proposed for more powerful feature expression for single image de-raining andSelf-attention based skip connections are proposed to symmetrically link convolutional and deconvolutional layers to exploit spatial contextual information better.
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 2026-10-15. 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.