Add files via upload

templates/challenge_phase_1_description.html

@@ -1 +1 @@
-<p>"Sed ut perspiciatis unde omnis iste natus error sit voluptatem accusantium doloremque laudantium, totam rem aperiam, eaque ipsa quae ab illo inventore veritatis et quasi architecto beatae vitae dicta sunt explicabo. Nemo enim ipsam voluptatem quia voluptas sit aspernatur aut odit aut fugit, sed quia consequuntur magni dolores eos qui ratione voluptatem sequi nesciunt. Neque porro quisquam est, qui dolorem ipsum quia dolor sit amet, consectetur, adipisci velit, sed quia non numquam eius modi tempora incidunt ut labore et dolore magnam aliquam quaerat voluptatem. Ut enim ad minima veniam, quis nostrum exercitationem ullam corporis suscipit laboriosam, nisi ut aliquid ex ea commodi consequatur? Quis autem vel eum iure reprehenderit qui in ea voluptate velit esse quam nihil molestiae consequatur, vel illum qui dolorem eum fugiat quo voluptas nulla pariatur?"</p>
+<p>We use testing images in <b>Scenes</b> to help participants test how to upload the JSON file for benchmarking. We further provide python scripts in the <a href="https://github.com/shenqq377/instance_detection_challenge">github repo</a> that walk you through how to preprocess raw data in our dataset and how to evaluate the results w.r.t the evaluation metrics.</p>

templates/challenge_phase_2_description.html

@@ -1 +1,4 @@
-"Sed ut perspiciatis unde omnis iste natus error sit voluptatem accusantium doloremque laudantium, totam rem aperiam, eaque ipsa quae ab illo inventore veritatis et quasi architecto beatae vitae dicta sunt explicabo. Nemo enim ipsam voluptatem quia voluptas sit aspernatur aut odit aut fugit, sed quia consequuntur magni dolores eos qui ratione voluptatem sequi nesciunt. Neque porro quisquam est, qui dolorem ipsum quia dolor sit amet, consectetur, adipisci velit, sed quia non numquam eius modi tempora incidunt ut labore et dolore magnam aliquam quaerat voluptatem. Ut enim ad minima veniam, quis nostrum exercitationem ullam corporis suscipit laboriosam, nisi ut aliquid ex ea commodi consequatur? Quis autem vel eum iure reprehenderit qui in ea voluptate velit esse quam nihil molestiae consequatur, vel illum qui dolorem eum fugiat quo voluptas nulla pariatur?"
+<p>This is the benchmarking phase. Scenes-Test (2.43 GB) will be officially released on Oct 20, 2024. We ask participants to upload a JSON file that scores for all the testing images in <b>Scenes-Test</b>.</p>
+<p><b>Top performing teams will be highlighted at Object Instance Detection Challenge Workshop at ACCV 2024.</b> All submissions before this end date will be considered for awards.</p>
+<p>The generated JSON or CSV file should adhere to the following dictionary format:</p>
+<img src="https://raw.githubusercontent.com/shenqq377/InsDetWorkshop-ACCV2024/challenge/templates/submission.png" width="80%" height="80%">

templates/description.html

@@ -1,3 +1,37 @@
-<p>"Sed ut perspiciatis unde omnis iste natus error sit voluptatem accusantium doloremque laudantium, totam rem aperiam, eaque ipsa quae ab illo inventore veritatis et quasi architecto beatae vitae dicta sunt explicabo. Nemo enim ipsam voluptatem quia voluptas sit aspernatur aut odit aut fugit, sed quia consequuntur magni dolores eos qui ratione voluptatem sequi nesciunt. Neque porro quisquam est, qui dolorem ipsum quia dolor sit amet, consectetur, adipisci velit, sed quia non numquam eius modi tempora incidunt ut labore et dolore magnam aliquam quaerat voluptatem. Ut enim ad minima veniam, quis nostrum exercitationem ullam corporis suscipit laboriosam, nisi ut aliquid ex ea commodi consequatur? Quis autem vel eum iure reprehenderit qui in ea voluptate velit esse quam nihil molestiae consequatur, vel illum qui dolorem eum fugiat quo voluptas nulla pariatur?"</p>
-
-<p>"Sed ut perspiciatis unde omnis iste natus error sit voluptatem accusantium doloremque laudantium, totam rem aperiam, eaque ipsa quae ab illo inventore veritatis et quasi architecto beatae vitae dicta sunt explicabo. Nemo enim ipsam voluptatem quia voluptas sit aspernatur aut odit aut fugit, sed quia consequuntur magni dolores eos qui ratione voluptatem sequi nesciunt. Neque porro quisquam est, qui dolorem ipsum quia dolor sit amet, consectetur, adipisci velit, sed quia non numquam eius modi tempora incidunt ut labore et dolore magnam aliquam quaerat voluptatem. Ut enim ad minima veniam, quis nostrum exercitationem ullam corporis suscipit laboriosam, nisi ut aliquid ex ea commodi consequatur? Quis autem vel eum iure reprehenderit qui in ea voluptate velit esse quam nihil molestiae consequatur, vel illum qui dolorem eum fugiat quo voluptas nulla pariatur?"</p>
+<h4>Introduction</h4>
+<center>
+  <img src="https://raw.githubusercontent.com/shenqq377/InsDetWorkshop-ACCV2024/challenge/templates/objdet-insdet.png" width="90%" height="90%">
+</center>
+<p><b>This challenge will be held at Object Instance Detection Challenge Workshop at ACCV 2024.</b></p>
+<p>Instance Detection (InsDet) is a practically important task in robotics applications, e.g., elderly-assistant robots need to fetch specific items from a cluttered kitchen, micro-fulfillment robots for the retail need to pick items from mixed boxes or shelves. Different from Object Detection (ObjDet) detecting all objects belonging to some predefined classes, InsDet aims to detect specific object instances defined by some examples capturing the instance from multiple views.</p>
+<p>This challenge focuses on the recently introduced InsDet dataset, which is larger in scale and more challenging than existing InsDet datasets. The major strengths of our InsDet dataset includes (1) both high-resolution profile images of object instances and high-resolution testing images from more realistic indoor scenes, simulating real-world indoor robots locating and recognizing object instances from a cluttered indoor scene in a distance (2) a realistic unified InsDet protocol to foster the InsDet research.</p>
+<p>Participants in this challenge will be tasked with predicting the bounding boxes for each given instance from testing images. This exciting opportunity allows researchers, students, and data scientists to apply their expertise in computer vision and machine learning to address instance detection problem. We refer participants to the <a href="https://docs.google.com/document/d/15R-R0tpKBy_KCNyc_8D45PQzHzyLmlPjDbntZJEBEYY/edit?usp=sharing">user guide</a> for details.</p>
+<h4>Important Dates</h4>
+<ul>
+<li>September 10, 2024, InsDet (6.60 GB) will be released.</li>
+<li>September 10, 2024, EvalAI server will be open.</li>
+<li>October 20, 2024, Scenes-Test (2.43 GB) will be released.</li>
+<li>November 25, 2024, Challenge will be closed.</li>
+<li>December 1, 2024, Invitation will be sent to some participants for presentation at the workshop.</li>
+<li>December 8, 2024, Workshop day.</li>
+</ul>
+<h4>Dataset</h4>
+<p>The dataset contains 100 object instances with multi-view profile images, 200 pure background images and 160 scene images. Participants can download the dataset from the <a href="https://drive.google.com/drive/folders/1rIRTtqKJGCTifcqJFSVvFshRb-sB0OzP?usp=sharing">InsDet</a> dataset.</p>
+<ol>
+<li><b>Objects.</b> 100 different Object instances. Each profile image has a resolution of 3072&times;3072 pixels (some instances are 3456&times;3456). Each instance is captured at 24 rotation positions (every 15&deg; in azimuth) with a 45&deg; elevation view.</li>
+<li><b>Background.</b> 200 high-resolution background images of indoor scenes that do not include any given instances from Objects.</li>
+<li><b>Scenes.</b> 160 high-resolution images (6144&times;8192) in cluttered scenes, where some instances are placed in reasonable locations. We tag these images as <i>easy</i> or <i>hard</i> based on scene clutter and object occlusion levels.</li>
+</ol>
+<h4>Benchmarking Protocols</h4>
+<ol>
+  <li><b>Goal.</b> Developing instance detectors using profile images and optionally some random background images. The detector should detect object instances of interest in real-world testing images.</li>
+  <li>
+    <p><b>Environment for model development.</b></p>
+    <ol type="a">
+      <li>A set of object instances, each of which has some visual examples captured from multiple views. Participants should develop a model to successfully detect these object instances.</li>
+      <li>Some random background images (not used in testing). Participants might use them to synthesize images. Participants can also download and use other external background images in training.</li>   
+    </ol>
+  </li>
+  <li><b>Environment for testing.</b> Real-world indoor scene images, in which participants' algorithms should detect object instances of interest.</li>
+</ol>
+<b>Importantly, participants are not allowed to develop any instance detectors on the Real-world indoor scene images we provided.</b> Furthermore, for participants who are invited for a presentation, we might ask for your code and models for verification.

templates/evaluation_details.html

@@ -1 +1,9 @@
-<p>"Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum."</p>
+<p>Following the COCO dataset, we tag testing object instances as small, medium, and large according to their bounding box area. The following 14 metrics are used for characterizing the performance of an instance detector on InsDet dataset. Additionally, we will also evaluate AP on <i>easy</i> and <i>hard</i> scenes separately.</p>
+<img src="https://raw.githubusercontent.com/shenqq377/InsDetWorkshop-ACCV2024/challenge/templates/evaluation_metrics.png" width="60%" height="60%">
+<p>
+<b>Note:</b>
+<ol>
+  <li>AP is average precision over all instances, which is traditionally called mean average precision (mAP).</li>
+</li>
+</ol>
+</p>

templates/terms_and_conditions.html

@@ -1 +1,9 @@
-<p>Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.</p>
+<p>Please refer to our data website. If you find our data useful, please cite:</p>
+<code>
+  @article{shen2024high, <br />
+  title={A High-Resolution Dataset for Instance Detection with Multi-View Object Capture}, <br />
+  author={Shen, Qianqian and Zhao, Yunhan and Kwon, Nahyun and Kim, Jeeeun and Li, Yanan and Kong, Shu}, <br />
+  journal={Advances in Neural Information Processing Systems}, <br />
+  volume={36},
+  year={2024}}
+</code>