add

content/dataset/00_RefAVS/_index.md

@@ -1,6 +1,6 @@
 ---
-title: Refer and Segment Objects in Audio-Visual Scenes (Ref-AVS) Dataset
-summary: Traditional reference segmentation tasks have predominantly focused on silent visual scenes, neglecting the integral role of multimodal perception and interaction in human experiences. In this work, we introduce a novel task called Reference Audio-Visual Segmentation (Ref-AVS), which seeks to segment objects within the visual domain based on expressions containing multimodal cues. Such expressions are articulated in natural language forms but are enriched with multimodal cues, including audio and visual descriptions.
+title: <b>Ref</b>er and Segment Objects in <b>A</b>udio-<b>V</b>isual <b>S</b>cenes (Ref-AVS) Dataset
+summary: In this work, we introduce a novel task called Reference Audio-Visual Segmentation (Ref-AVS), which seeks to segment objects within the visual domain based on expressions containing multimodal cues. 
 dataset: true
 # Optional external URL for project (replaces project detail page).
 external_link: https://github.com/GeWu-Lab/Ref-AVS

content/dataset/01_LFAV/_index.md

@@ -1,5 +1,5 @@
 ---
-title: <b>L</b>ong <b>F</b>orm <b>A</b>udio-<b>V</b>isual (<b>LFAV<b>) Dataset
+title: <b>L</b>ong <b>F</b>orm <b>A</b>udio-<b>V</b>isual (<b>LFAV</b>) Dataset
 summary: To achieve a better understanding of long form audio-visual videos, we propose to focus on the multisensory temporal event localization task, which essentially requires the model to predict the start and end time of each audio and visual event in the video. Concretely, we divide the video into several non-overlapping snippets, then predict the event categories of all snippets. To study the proposed multisensory temporal event localization task, we elaborately build a large-scale Long Form Audio-visual Video (LFAV) dataset with an average video length of 210 seconds and a total video length of 302 hours.
 dataset: true
 # Optional external URL for project (replaces project detail page).

content/publication/Balanced Multimodal Learning via On-the-fly Gradient Modulation/index.md

@@ -1,5 +1,5 @@
 ---  
-title: "Balanced Multimodal Learning via On-the-fly Gradient Modulation (CVPR Oral)"  
+title: "Balanced Multimodal Learning via On-the-fly Gradient Modulation"  
 authors:  
  - Xiaokang Peng*  
  - Yake Wei*  
@@ -8,6 +8,7 @@ authors:
  - Di Hu
 publication_types: ["1"]  
 publication: Computer Vision and Pattern Recognition(CVPR) 2022 <b>Oral Presentation</b>  
+is_oral: True
 publication_types_name: Conference Paper  
 url_pdf: https://arxiv.org/abs/2203.15332  
 url_code: https://github.com/GeWu-Lab/OGM-GE_CVPR2022  

content/publication/Can Textual Semantics Mitigate Sounding Object SegmentationPreference_/cite.bib

@@ -0,0 +1,6 @@
+@article{wang2024can,
+  title={Can Textual Semantics Mitigate Sounding Object Segmentation Preference?},
+  author={Wang, Yaoting and Sun, Peiwen and Li, Yuanchao and Zhang, Honggang and Hu, Di},
+  journal={arXiv preprint arXiv:2407.10947},
+  year={2024}
+}

content/publication/KOI_ Accelerating Online Imitation Learning via Hybrid Key-state Guidance/index.md

@@ -12,6 +12,7 @@ publication_types: ["9"]
 publication: Conference on Robot Learning (CoRL)  
 publication_types_name: Conference Paper  
 url_pdf: https://www.arxiv.org/abs/2408.02912
+url_code: https://github.com/GeWu-Lab/Keystate_Online_Imitation
 topic_types: ["2"]
 topic_types_name: topic_scene_understanding
 rating : 2024_09_01

content/publication/Learning to Answer Questions in Dynamic Audio-Visual Scenarios/index.md

@@ -14,6 +14,7 @@ url_pdf: https://arxiv.org/abs/2203.14072
 url_code: https://github.com/GeWu-Lab/MUSIC-AVQA  
 url_project: https://gewu-lab.github.io/MUSIC-AVQA/  
 topic_types: ["2"]
+is_oral: True
 topic_types_name: topic_scene_understanding
 rating : 2022_03_04
 ---  

content/publication/MMPareto_ Innocent Uni-modal Assistance for Enhanced Multi-modal Learning/cite.bib

@@ -0,0 +1,6 @@
+@article{wei2024mmpareto,
+  title={MMPareto: Boosting Multimodal Learning with Innocent Unimodal Assistance},
+  author={Wei, Yake and Hu, Di},
+  journal={arXiv preprint arXiv:2405.17730},
+  year={2024}
+}

content/publication/MMPareto_ Innocent Uni-modal Assistance for Enhanced Multi-modal Learning/index.md

@@ -7,6 +7,7 @@ publication_types: ["1"]
 publication: International Conference on Machine Learning(ICML) 2024
 publication_types_name: Conference Paper  
 url_pdf: https://openreview.net/pdf?id=JHD4Q4GbXa
+url_code: https://github.com/GeWu-Lab/MMPareto_ICML2024
 topic_types: ["2"]
 topic_types_name: topic_mechanism
 rating : 2024_05_06

content/publication/On-the-fly Modulation for Balanced Multimodal Learning/cite.bib

@@ -0,0 +1,7 @@
+@article{wei2024fly,
+  title={On-the-fly Modulation for Balanced Multimodal Learning},
+  author={Wei, Yake and Hu, Di and Du, Henghui and Wen, Ji-Rong},
+  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
+  year={2024},
+  publisher={IEEE}
+}

content/publication/Play to the Score_ Stage-Guided Dynamic Multi-Sensory Fusion for Robotic Manipulation/index.md

@@ -6,6 +6,7 @@ authors:
  - Wenke Ma  
  - Xuelong Li  
 publication_types: ["9"]  
+is_oral: True
 publication: Conference on Robot Learning (CoRL)  
 publication_types_name: Conference Paper  
 url_pdf: https://arxiv.org/pdf/2408.01366

content/publication/Ref-AVS_ Refer and Segment Objects in Audio-Visual Scenes/cite.bib

@@ -0,0 +1,6 @@
+@article{wang2024ref,
+  title={Ref-avs: Refer and segment objects in audio-visual scenes},
+  author={Wang, Yaoting and Sun, Peiwen and Zhou, Dongzhan and Li, Guangyao and Zhang, Honggang and Hu, Di},
+  journal={arXiv preprint arXiv:2407.10957},
+  year={2024}
+}

content/publication/Stepping Stones_ A Progressive Training Strategy for Audio-Visual Semantic Segmentation/cite.bib

@@ -0,0 +1,6 @@
+@article{ma2024steppingstones,
+          title={Stepping Stones: A Progressive Training Strategy for Audio-Visual Semantic Segmentation},
+          author={Ma, Juncheng and Sun, Peiwen and Wang, Yaoting and Hu, Di},
+          journal={IEEE European Conference on Computer Vision (ECCV)},
+          year={2024},
+         }

docs/authors/andong-deng/index.html

@@ -387,7 +387,7 @@ <h3>Latest</h3>
       <ul>
 
         <li>
-          <a href="/publication/balanced-multimodal-learning-via-on-the-fly-gradient-modulation/">Balanced Multimodal Learning via On-the-fly Gradient Modulation (CVPR Oral)</a>
+          <a href="/publication/balanced-multimodal-learning-via-on-the-fly-gradient-modulation/">Balanced Multimodal Learning via On-the-fly Gradient Modulation</a>
         </li>
 
         <li>

docs/authors/andong-deng/index.xml

@@ -13,7 +13,7 @@
     </image>
 
     <item>
-      <title>Balanced Multimodal Learning via On-the-fly Gradient Modulation (CVPR Oral)</title>
+      <title>Balanced Multimodal Learning via On-the-fly Gradient Modulation</title>
       <link>/publication/balanced-multimodal-learning-via-on-the-fly-gradient-modulation/</link>
       <pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate>
       <guid>/publication/balanced-multimodal-learning-via-on-the-fly-gradient-modulation/</guid>

docs/authors/di-hu/index.html

@@ -399,7 +399,7 @@ <h3>Latest</h3>
         </li>
 
         <li>
-          <a href="/publication/balanced-multimodal-learning-via-on-the-fly-gradient-modulation/">Balanced Multimodal Learning via On-the-fly Gradient Modulation (CVPR Oral)</a>
+          <a href="/publication/balanced-multimodal-learning-via-on-the-fly-gradient-modulation/">Balanced Multimodal Learning via On-the-fly Gradient Modulation</a>
         </li>
 
         <li>

docs/authors/di-hu/index.xml

@@ -37,7 +37,7 @@
     </item>
 
     <item>
-      <title>Balanced Multimodal Learning via On-the-fly Gradient Modulation (CVPR Oral)</title>
+      <title>Balanced Multimodal Learning via On-the-fly Gradient Modulation</title>
       <link>/publication/balanced-multimodal-learning-via-on-the-fly-gradient-modulation/</link>
       <pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate>
       <guid>/publication/balanced-multimodal-learning-via-on-the-fly-gradient-modulation/</guid>

docs/authors/dong-wang/index.html

@@ -387,7 +387,7 @@ <h3>Latest</h3>
       <ul>
 
         <li>
-          <a href="/publication/balanced-multimodal-learning-via-on-the-fly-gradient-modulation/">Balanced Multimodal Learning via On-the-fly Gradient Modulation (CVPR Oral)</a>
+          <a href="/publication/balanced-multimodal-learning-via-on-the-fly-gradient-modulation/">Balanced Multimodal Learning via On-the-fly Gradient Modulation</a>
         </li>
 
         <li>

docs/authors/dong-wang/index.xml

@@ -13,7 +13,7 @@
     </image>
 
     <item>
-      <title>Balanced Multimodal Learning via On-the-fly Gradient Modulation (CVPR Oral)</title>
+      <title>Balanced Multimodal Learning via On-the-fly Gradient Modulation</title>
       <link>/publication/balanced-multimodal-learning-via-on-the-fly-gradient-modulation/</link>
       <pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate>
       <guid>/publication/balanced-multimodal-learning-via-on-the-fly-gradient-modulation/</guid>

docs/authors/haojin-yang/index.html

@@ -390,6 +390,10 @@ <h3>Latest</h3>
           <a href="/publication/not-all-knowledge-is-created-equal/">Not All Knowledge Is Created Equal</a>
         </li>
 
+        <li>
+          <a href="/publication/not-all-knowledge-is-created-equal/">Not All Knowledge Is Created Equal</a>
+        </li>
+
         <li>
           <a href="/publication/supervised-knowledge-may-hurt-novel-class-discovery-performance/">Supervised Knowledge May Hurt Novel Class Discovery Performance</a>
         </li>

docs/authors/haojin-yang/index.xml

@@ -20,6 +20,14 @@
       <description></description>
     </item>
 
+    <item>
+      <title>Not All Knowledge Is Created Equal</title>
+      <link>/publication/not-all-knowledge-is-created-equal/</link>
+      <pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate>
+      <guid>/publication/not-all-knowledge-is-created-equal/</guid>
+      <description></description>
+    </item>
+
     <item>
       <title>Supervised Knowledge May Hurt Novel Class Discovery Performance</title>
       <link>/publication/supervised-knowledge-may-hurt-novel-class-discovery-performance/</link>