Update papers.bib

_bibliography/papers.bib

@@ -3,7 +3,7 @@ @inproceedings{lee2021regularization
   abbr={CVPR},
   title={Regularization strategy for point cloud via rigidly mixed sample},
   author={Lee, Dogyoon and Lee, Jaeha and Lee, Junhyeop and Lee, Hyeongmin and Lee, Minhyeok and Woo, Sungmin and Lee, Sangyoun},
-  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
+  booktitle={[CVPR 2021] Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
   pages={15900--15909},
   year={2021},
   arxiv={2102.01929},
@@ -17,7 +17,7 @@ @inproceedings{lee2022robust
   abbr={WACV},
   title={Robust lane detection via expanded self attention},
   author={Lee, Minhyeok and Lee, Junhyeop and Lee, Dogyoon and Kim, Woojin and Hwang, Sangwon and Lee, Sangyoun},
-  booktitle={Proceedings of the IEEE/CVF winter conference on applications of computer vision},
+  booktitle={[WACV 2022] Proceedings of the IEEE/CVF winter conference on applications of computer vision},
   pages={533--542},
   year={2022},
   arxiv={2102.07037},
@@ -31,7 +31,7 @@ @inproceedings{lee2023unsupervised
   abbr={WACV},
   title={Unsupervised Video Object Segmentation via Prototype Memory Network},
   author={Lee, Minhyeok and Cho, Suhwan and Lee, Seunghoon and Park, Chaewon and Lee, Sangyoun},
-  booktitle={Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision},
+  booktitle={[WACV 2023] Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision},
   pages={5924--5934},
   year={2023},
   arxiv={2209.03712},
@@ -45,7 +45,7 @@ @inproceedings{cho2022tackling
   abbr={ECCV},
   title={Tackling background distraction in video object segmentation},
   author={Cho, Suhwan and Lee, Heansung and Lee, Minhyeok and Park, Chaewon and Jang, Sungjun and Kim, Minjung and Lee, Sangyoun},
-  booktitle={Computer Vision--ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23--27, 2022, Proceedings, Part XXII},
+  booktitle={[ECCV 2022] Computer Vision--ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23--27, 2022, Proceedings, Part XXII},
   pages={446--462},
   year={2022},
   organization={Springer},
@@ -59,7 +59,7 @@ @inproceedings{park2022saliency
   addr={ICIP},
   title={Saliency detection via global context enhanced feature fusion and edge weighted loss},
   author={Park, Chaewon and Lee, Minhyeok and Cho, MyeongAh and Lee, Sangyoun},
-  booktitle={2022 IEEE International Conference on Image Processing (ICIP)},
+  booktitle={[ICIP 2022] 2022 IEEE International Conference on Image Processing},
   pages={811--815},
   year={2022},
   organization={IEEE},
@@ -72,7 +72,7 @@ @inproceedings{lee2022superpixel
   addr={ICIP},
   title={Superpixel Group-Correlation Network for Co-Saliency Detection},
   author={Lee, Minhyeok and Park, Chaewon and Cho, Suhwan and Lee, Sangyoun},
-  booktitle={2022 IEEE International Conference on Image Processing (ICIP)},
+  booktitle={[ICIP 2022] 2022 IEEE International Conference on Image Processing},
   pages={806--810},
   year={2022},
   organization={IEEE},
@@ -95,7 +95,7 @@ @article{lee2023adaptive
   addr={ICIP},
   title={Adaptive Graph Convolution Module for Salient Object Detection},
   author={Lee, Yongwoo and Lee, Minhyeok and Cho, Suhwan and Lee, Sangyoun},
-  journal={2023 IEEE International Conference on Image Processing (ICIP)},
+  journal={[ICIP 2023] 2023 IEEE International Conference on Image Processing},
   year={2023},
   arxiv={2303.09801},
   abstract={Salient object detection (SOD) is a task that involves identifying and segmenting the most visually prominent object in an image. Existing solutions can accomplish this use a multi-scale feature fusion mechanism to detect the global context of an image. However, as there is no consideration of the structures in the image nor the relations between distant pixels, conventional methods cannot deal with complex scenes effectively. In this paper, we propose an adaptive graph convolution module (AGCM) to overcome these limitations. Prototype features are initially extracted from the input image using a learnable region generation layer that spatially groups features in the image. The prototype features are then refined by propagating information between them based on a graph architecture, where each feature is regarded as a node. Experimental results show that the proposed AGCM dramatically improves the SOD performance both quantitatively and quantitatively.},
@@ -118,7 +118,7 @@ @inproceedings{lee2022spsn
   abbr={ECCV},
   title={Spsn: Superpixel prototype sampling network for rgb-d salient object detection},
   author={Lee, Minhyeok and Park, Chaewon and Cho, Suhwan and Lee, Sangyoun},
-  booktitle={Computer Vision--ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23--27, 2022, Proceedings, Part XXIX},
+  booktitle={[ECCV 2022] Computer Vision--ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23--27, 2022, Proceedings, Part XXIX},
   pages={630--647},
   year={2022},
   organization={Springer},
@@ -133,7 +133,7 @@ @inproceedings{park2022fastano
   abbr={WACV},
   title={FastAno: Fast anomaly detection via spatio-temporal patch transformation},
   author={Park, Chaewon and Cho, MyeongAh and Lee, Minhyeok and Lee, Sangyoun},
-  booktitle={Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision},
+  booktitle={[WACV 2022] Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision},
   pages={2249--2259},
   year={2022},
   arxiv={2106.08613},
@@ -142,10 +142,11 @@ @inproceedings{park2022fastano
 }
 
 @inproceedings{lee2023hierarchically,
+  selected={true},
   abbr={ICCV},
   title={Hierarchically decomposed graph convolutional networks for skeleton-based action recognition},
   author={Lee, Jungho and Lee, Minhyeok and Lee, Dogyoon and Lee, Sangyoun},
-  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
+  booktitle={[ICCV 2023] Proceedings of the IEEE/CVF International Conference on Computer Vision},
   pages={10444--10453},
   year={2023},
   arxiv={2208.10741},
@@ -159,7 +160,7 @@ @inproceedings{lee2022edgeconv
   abbr={WACV},
   title={Edgeconv with attention module for monocular depth estimation},
   author={Lee, Minhyeok and Hwang, Sangwon and Park, Chaewon and Lee, Sangyoun},
-  booktitle={Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision},
+  booktitle={[WACV 2022] Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision},
   pages={2858--2867},
   year={2022},
   arxiv={2106.08615},
@@ -172,7 +173,7 @@ @inproceedings{cho2023treating
   abbr={WACV},
   title={Treating motion as option to reduce motion dependency in unsupervised video object segmentation},
   author={Cho, Suhwan and Lee, Minhyeok and Lee, Seunghoon and Park, Chaewon and Kim, Donghyeong and Lee, Sangyoun},
-  booktitle={Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision},
+  booktitle={[WACV 2023] Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision},
   pages={5140--5149},
   year={2023},
   arxiv={2209.03138},
@@ -185,7 +186,7 @@ @article{lee2023tsanet
   addr={ICIP},
   title={TSANET: Temporal and Scale Alignment for Unsupervised Video Object Segmentation},
   author={Lee, Seunghoon and Cho, Suhwan and Lee, Dogyoon and Lee, Minhyeok and Lee, Sangyoun},
-  journal={2023 IEEE International Conference on Image Processing (ICIP)},
+  journal={[ICIP 2023] 2023 IEEE International Conference on Image Processing},
   year={2023},
   arxiv={2303.04376},
   abstract={Unsupervised Video Object Segmentation (UVOS) refers to the challenging task of segmenting the prominent object in videos without manual guidance. In other words, the network detects the accurate region of the target object in a sequence of RGB frames without prior knowledge. In recent works, two approaches for UVOS have been discussed that can be divided into: appearance and appearance-motion based methods. Appearance based methods utilize the correlation information of inter-frames to capture target object that commonly appears in a sequence. However, these methods does not consider the motion of target object due to exploit the correlation information between randomly paired frames. Appearance-motion based methods, on the other hand, fuse the appearance features from RGB frames with the motion features from optical flow. Motion cue provides useful information since salient objects typically show distinctive motion in a sequence. However, these approaches have the limitation that the dependency on optical flow is dominant. In this paper, we propose a novel framework for UVOS that can address aforementioned limitations of two approaches in terms of both time and scale. Temporal Alignment Fusion aligns the saliency information of adjacent frames with the target frame to leverage the information of adjacent frames. Scale Alignment Decoder predicts the target object mask precisely by aggregating differently scaled feature maps via continuous mapping with implicit neural representation. We present experimental results on public benchmark datasets, DAVIS 2016 and FBMS, which demonstrate the effectiveness of our method. Furthermore, we outperform the state-of-the-art methods on DAVIS 2016.},
@@ -196,19 +197,19 @@ @article{park2023two
   addr={ICASSP},
   title={Two-stream Decoder Feature Normality Estimating Network for Industrial Anomaly Detection},
   author={Park, Chaewon and Lee, Minhyeok and Cho, Suhwan and Kim, Donghyeong and Lee, Sangyoun},
-  journal={IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2023},
+  journal={[ICASSP 2023] IEEE International Conference on Acoustics, Speech and Signal Processing 2023},
   year={2023},
   arxiv={2302.09794},
   abstract={Image reconstruction-based anomaly detection has recently been in the spotlight because of the difficulty of constructing anomaly datasets. These approaches work by learning to model normal features without seeing abnormal samples during training and then discriminating anomalies at test time based on the reconstructive errors. However, these models have limitations in reconstructing the abnormal samples due to their indiscriminate conveyance of features. Moreover, these approaches are not explicitly optimized for distinguishable anomalies. To address these problems, we propose a two-stream decoder network (TSDN), designed to learn both normal and abnormal features. Additionally, we propose a feature normality estimator (FNE) to eliminate abnormal features and prevent high-quality reconstruction of abnormal regions. Evaluation on a standard benchmark demonstrated performance better than state-of-the-art models.},
   preview={TSDN.png}
 }
 
-@article{lee2022leveraging,
-  selected={true},
+@inproceedings{lee2023leveraging,
   addr={ICCV},
-  title={Leveraging Spatio-Temporal Dependency for Skeleton-Based Action Recognition},
-  author={Lee, Jungho and Lee, Minhyeok and Cho, Suhwan and Woo, Sungmin and Lee, Sangyoun},
-  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
+  title={Leveraging spatio-temporal dependency for skeleton-based action recognition},
+  author={Lee, Jungho and Lee, Minhyeok and Cho, Suhwan and Woo, Sungmin and Jang, Sungjun and Lee, Sangyoun},
+  booktitle={[ICCV 2023] Proceedings of the IEEE/CVF International Conference on Computer Vision},
+  pages={10255--10264},
   year={2023},
   arxiv={2212.04761},
   abstract={Skeleton-based action recognition has attracted considerable attention due to its compact skeletal structure of the human body. Many recent methods have achieved remarkable performance using graph convolutional networks (GCNs) and convolutional neural networks (CNNs), which extract spatial and temporal features, respectively. Although spatial and temporal dependencies in the human skeleton have been explored, spatio-temporal dependency is rarely considered. In this paper, we propose the Inter-Frame Curve Network (IFC-Net) to effectively leverage the spatio-temporal dependency of the human skeleton. Our proposed network consists of two novel elements: 1) The Inter-Frame Curve (IFC) module; and 2) Dilated Graph Convolution (D-GC). The IFC module increases the spatio-temporal receptive field by identifying meaningful node connections between every adjacent frame and generating spatio-temporal curves based on the identified node connections. The D-GC allows the network to have a large spatial receptive field, which specifically focuses on the spatial domain. The kernels of D-GC are computed from the given adjacency matrices of the graph and reflect large receptive field in a way similar to the dilated CNNs. Our IFC-Net combines these two modules and achieves state-of-the-art performance on three skeleton-based action recognition benchmarks: NTU-RGB+D 60, NTU-RGB+D 120, and Northwestern-UCLA.},
@@ -220,7 +221,7 @@ @inproceedings{Lee_2023_CVPR
   abbr={CVPR},
   title={DP-NeRF: Deblurred Neural Radiance Field With Physical Scene Priors},
   author={Lee, Dogyoon and Lee, Minhyeok and Shin, Chajin and Lee, Sangyoun},
-  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
+  booktitle={[CVPR 2023] Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
   pages={12386-12396},
   year={2023},
   arxiv={2211.12046},
@@ -271,6 +272,6 @@ @inproceedings{lee2021multi
   pages={1--4},
   year={2021},
   organization={IEEE},
-  abstract={Monocular depth estimation is a fundamental task in autonomous driving, robotics, virtual reality. Monocular depth estimation is attracting research due to the efficiency of predicting depth map from a single RGB image. However, Monocular depth estimation is an ill-posed problem and is sensitive to image compositions such as light condition, occlusion, noise. We propose an encoder-decoder based network that uses multi-level attention and aggregate densely weighted feature map. Our model is evaluated on NYU Depth v2. Experimental results demonstrated that our model achieves promising performance.},
+  abstract={[ICCE-Asia 2021] Monocular depth estimation is a fundamental task in autonomous driving, robotics, virtual reality. Monocular depth estimation is attracting research due to the efficiency of predicting depth map from a single RGB image. However, Monocular depth estimation is an ill-posed problem and is sensitive to image compositions such as light condition, occlusion, noise. We propose an encoder-decoder based network that uses multi-level attention and aggregate densely weighted feature map. Our model is evaluated on NYU Depth v2. Experimental results demonstrated that our model achieves promising performance.},
   preview={MFMA.png}
 }