paper-conference | Wenxi Li's Personal Pagehttps://liwenxi.github.io/publication-type/paper-conference/paper-conferenceHugo Blox Builder (https://hugoblox.com)en-usThu, 01 Jan 2026 00:00:00 +0000https://liwenxi.github.io/media/icon_hu1d4110f592c674cb4c7228ceeb4bd0a4_223499_512x512_fill_lanczos_center_3.pngpaper-conferencehttps://liwenxi.github.io/publication-type/paper-conference/2D-CrossScan Mamba: Enhancing State Space Models with Spatially Consistent Multi-Path 2D Information Propagationhttps://liwenxi.github.io/publication/2d-crossscan-mamba-2026/Thu, 01 Jan 2026 00:00:00 +0000https://liwenxi.github.io/publication/2d-crossscan-mamba-2026/AWP: Activation-based Window Pruning for Gigapixel Object Detectionhttps://liwenxi.github.io/publication/awp-2026/Thu, 01 Jan 2026 00:00:00 +0000https://liwenxi.github.io/publication/awp-2026/BiHashFormer: Hash-Driven Dual-Branch Transformer for Efficient Object Detection in HRW Shotshttps://liwenxi.github.io/publication/bihashformer-2026/Thu, 01 Jan 2026 00:00:00 +0000https://liwenxi.github.io/publication/bihashformer-2026/ElasticFormer: Detecting Objects in HRW Shots via Elastic Computing Vision Transformerhttps://liwenxi.github.io/publication/elasticformer-2026/Thu, 01 Jan 2026 00:00:00 +0000https://liwenxi.github.io/publication/elasticformer-2026/GigaMoE: Sparsity-Guided Mixture of Experts for Efficient Gigapixel Object Detectionhttps://liwenxi.github.io/publication/gigamoe-2026/Thu, 01 Jan 2026 00:00:00 +0000https://liwenxi.github.io/publication/gigamoe-2026/SpanFormer: Multi-Level Adaptive Sparsity for Object Detection in High-Resolution Wide Shotshttps://liwenxi.github.io/publication/spanformer-2026/Thu, 01 Jan 2026 00:00:00 +0000https://liwenxi.github.io/publication/spanformer-2026/SparseFormer: Detecting Objects in HRW Shots via Sparse Vision Transformerhttps://liwenxi.github.io/publication/li2024mm/Mon, 05 Aug 2024 00:00:00 +0000https://liwenxi.github.io/publication/li2024mm/<!-- <div class="alert alert-note"> <div> Click the <em>Cite</em> button above to demo the feature to enable visitors to import publication metadata into their reference management software. </div> </div> <div class="alert alert-note"> <div> Create your slides in Markdown - click the <em>Slides</em> button to check out the example. </div> </div> --> <!-- Add the publication's **full text** or **supplementary notes** here. You can use rich formatting such as including [code, math, and images](https://docs.hugoblox.com/content/writing-markdown-latex/). -->SaccadeMOT: Enhancing Object Detection and Tracking in Gigapixel Images via Scale-Aware Density Estimationhttps://liwenxi.github.io/publication/li2024ecai/Fri, 05 Jul 2024 00:00:00 +0000https://liwenxi.github.io/publication/li2024ecai/<!-- <div class="alert alert-note"> <div> Click the <em>Cite</em> button above to demo the feature to enable visitors to import publication metadata into their reference management software. </div> </div> <div class="alert alert-note"> <div> Create your slides in Markdown - click the <em>Slides</em> button to check out the example. </div> </div> --> <!-- Add the publication's **full text** or **supplementary notes** here. You can use rich formatting such as including [code, math, and images](https://docs.hugoblox.com/content/writing-markdown-latex/). -->SaccadeDet: A Novel Dual-Stage Architecture for Rapid and Accurate Detection in Gigapixel Imageshttps://liwenxi.github.io/publication/li2024ecml/Thu, 30 May 2024 00:00:00 +0000https://liwenxi.github.io/publication/li2024ecml/<!-- <div class="alert alert-note"> <div> Click the <em>Cite</em> button above to demo the feature to enable visitors to import publication metadata into their reference management software. </div> </div> <div class="alert alert-note"> <div> Create your slides in Markdown - click the <em>Slides</em> button to check out the example. </div> </div> --> <!-- Add the publication's **full text** or **supplementary notes** here. You can use rich formatting such as including [code, math, and images](https://docs.hugoblox.com/content/writing-markdown-latex/). -->Semantic Enrichment for Video Question Answering with Gated Graph Neural Networkshttps://liwenxi.github.io/publication/lyu2024icassp/Sun, 14 Apr 2024 00:00:00 +0000https://liwenxi.github.io/publication/lyu2024icassp/<!-- <div class="alert alert-note"> <div> Click the <em>Cite</em> button above to demo the feature to enable visitors to import publication metadata into their reference management software. </div> </div> <div class="alert alert-note"> <div> Create your slides in Markdown - click the <em>Slides</em> button to check out the example. </div> </div> --> <!-- Add the publication's **full text** or **supplementary notes** here. You can use rich formatting such as including [code, math, and images](https://docs.hugoblox.com/content/writing-markdown-latex/). -->GigaHumanDet: Exploring Full-body Detection on Gigapixel-level Imageshttps://liwenxi.github.io/publication/liu2024aaai/Tue, 20 Feb 2024 00:00:00 +0000https://liwenxi.github.io/publication/liu2024aaai/<!-- <div class="alert alert-note"> <div> Click the <em>Cite</em> button above to demo the feature to enable visitors to import publication metadata into their reference management software. </div> </div> <div class="alert alert-note"> <div> Create your slides in Markdown - click the <em>Slides</em> button to check out the example. </div> </div> --> <!-- Add the publication's **full text** or **supplementary notes** here. You can use rich formatting such as including [code, math, and images](https://docs.hugoblox.com/content/writing-markdown-latex/). -->Graph-Based Video-Language Learning with Multi-Grained Audio-Visual Alignmenthttps://liwenxi.github.io/publication/lyu2023mm/Thu, 20 Jul 2023 00:00:00 +0000https://liwenxi.github.io/publication/lyu2023mm/<!-- <div class="alert alert-note"> <div> Click the <em>Cite</em> button above to demo the feature to enable visitors to import publication metadata into their reference management software. </div> </div> <div class="alert alert-note"> <div> Create your slides in Markdown - click the <em>Slides</em> button to check out the example. </div> </div> --> <!-- Add the publication's **full text** or **supplementary notes** here. You can use rich formatting such as including [code, math, and images](https://docs.hugoblox.com/content/writing-markdown-latex/). -->Gated Multi-modal Fusion with Cross-modal Contrastive Learning for Video Question Answeringhttps://liwenxi.github.io/publication/lyu2023icann/Tue, 20 Jun 2023 00:00:00 +0000https://liwenxi.github.io/publication/lyu2023icann/<!-- <div class="alert alert-note"> <div> Click the <em>Cite</em> button above to demo the feature to enable visitors to import publication metadata into their reference management software. </div> </div> <div class="alert alert-note"> <div> Create your slides in Markdown - click the <em>Slides</em> button to check out the example. </div> </div> --> <!-- Add the publication's **full text** or **supplementary notes** here. You can use rich formatting such as including [code, math, and images](https://docs.hugoblox.com/content/writing-markdown-latex/). -->