Min-Hung (Steve) Chen

The main progress for action segmentation comes from densely-annotated data for fully-supervised learning. Since manual annotation for frame-level actions is timeconsuming and challenging, we propose to exploit auxiliary unlabeled videos, which are much easier to obtain, by shaping this problem as a domain adaptation (DA) problem. Although various DA techniques have been proposed in recent years, most of them have been developed only for the spatial direction. Therefore, we propose Mixed… Show more

The main progress for action segmentation comes from densely-annotated data for fully-supervised learning. Since manual annotation for frame-level actions is timeconsuming and challenging, we propose to exploit auxiliary unlabeled videos, which are much easier to obtain, by shaping this problem as a domain adaptation (DA) problem. Although various DA techniques have been proposed in recent years, most of them have been developed only for the spatial direction. Therefore, we propose Mixed Temporal Domain Adaptation (MTDA) to jointly align frame- and video-level embedded feature spaces across domains, and further integrate with the domain attention mechanism to focus on aligning the frame-level features with higher domain discrepancy, leading to more effective domain adaptation. Finally, we evaluate our proposed methods on three challenging datasets (GTEA, 50Salads, and Breakfast), and validate that MTDA outperforms the current state-of-the-art methods on all three datasets by large margins (e.g. 6.4% gain on F1@50 and 6.8% gain on the edit score for GTEA). Show less

Performing driving behaviors based on causal reasoning is essential to ensure driving safety. In this work, we investigated how state-of-the-art 3D Convolutional Neural Networks (CNNs) perform on classifying driving behaviors based on causal reasoning. We proposed a perturbation-based visual explanation method to inspect the models' performance visually. By examining the video attention saliency, we found that existing models could not precisely capture the causes (eg, traffic light) of the… Show more

Performing driving behaviors based on causal reasoning is essential to ensure driving safety. In this work, we investigated how state-of-the-art 3D Convolutional Neural Networks (CNNs) perform on classifying driving behaviors based on causal reasoning. We proposed a perturbation-based visual explanation method to inspect the models' performance visually. By examining the video attention saliency, we found that existing models could not precisely capture the causes (eg, traffic light) of the specific action (eg, stopping). Therefore, the Temporal Reasoning Block (TRB) was proposed and introduced to the models. With the TRB models, we achieved the accuracy of , which outperform the state-of-the-art 3D CNNs from previous works. The attention saliency also demonstrated that TRB helped models focus on the causes more precisely. With both numerical and visual evaluations, we concluded that our proposed TRB models were able to provide accurate driving behavior prediction by learning the causal reasoning of the behaviors. Show less

Although various image-based domain adaptation (DA) techniques have been proposed in recent years, domain shift in videos is still not well-explored. Most previous works only evaluate performance on small-scale datasets which are saturated. Therefore, we first propose two large-scale video DA datasets with much larger domain discrepancy: UCF-HMDB_full and Kinetics-Gameplay. Second, we investigate different DA integration methods for videos, and show that simultaneously aligning and learning… Show more

Although various image-based domain adaptation (DA) techniques have been proposed in recent years, domain shift in videos is still not well-explored. Most previous works only evaluate performance on small-scale datasets which are saturated. Therefore, we first propose two large-scale video DA datasets with much larger domain discrepancy: UCF-HMDB_full and Kinetics-Gameplay. Second, we investigate different DA integration methods for videos, and show that simultaneously aligning and learning temporal dynamics achieves effective alignment even without sophisticated DA methods. Finally, we propose Temporal Attentive Adversarial Adaptation Network (TA3N), which explicitly attends to the temporal dynamics using domain discrepancy for more effective domain alignment, achieving state-of-the-art performance on four video DA datasets (e.g. 7.9% accuracy gain over “Source only” from 73.9% to 81.8% on “HMDB --> UCF”, and 10.3% gain on “Kinetics --> Gameplay”). Show less

Traffic signs are critical for maintaining the safety and efficiency of our roads. Therefore, we need to carefully assess the capabilities and limitations of automated traffic sign detection systems. Existing traffic sign datasets are limited in terms of type and severity of challenging conditions. Metadata corresponding to these conditions are unavailable and it is not possible to investigate the effect of a single factor because of the simultaneous changes in numerous conditions. To overcome… Show more

Traffic signs are critical for maintaining the safety and efficiency of our roads. Therefore, we need to carefully assess the capabilities and limitations of automated traffic sign detection systems. Existing traffic sign datasets are limited in terms of type and severity of challenging conditions. Metadata corresponding to these conditions are unavailable and it is not possible to investigate the effect of a single factor because of the simultaneous changes in numerous conditions. To overcome the shortcomings in existing datasets, we introduced the CURE-TSD-Real dataset, which is based on simulated challenging conditions that correspond to adversaries that can occur in real-world environments and systems. We test the performance of two benchmark algorithms and show that severe conditions can result in an average performance degradation of 29% in precision and 68% in recall. We investigate the effect of challenging conditions through spectral analysis and show that the challenging conditions can lead to distinct magnitude spectrum characteristics. Moreover, we show that mean magnitude spectrum of changes in video sequences under challenging conditions can be an indicator of detection performance. The CURE-TSD-Real dataset is available online at https://github.com/olivesgatech/CURE-TSD. Show less

Image captioning has attracted considerable attention in recent years. However, little work has been done for game image captioning which has some unique characteristics and requirements. In this work we propose a novel game image captioning model which integrates bottom-up attention with a new multi-level residual top-down attention mechanism. Firstly, a lower-level residual top-down attention network is added to the Faster R-CNN based bottom-up attention network to address the problem that… Show more

Image captioning has attracted considerable attention in recent years. However, little work has been done for game image captioning which has some unique characteristics and requirements. In this work we propose a novel game image captioning model which integrates bottom-up attention with a new multi-level residual top-down attention mechanism. Firstly, a lower-level residual top-down attention network is added to the Faster R-CNN based bottom-up attention network to address the problem that the latter may lose important spatial information when extracting regional features. Secondly, an upper-level residual top-down attention network is implemented in the caption generation network to better fuse the extracted regional features for subsequent caption prediction. We create two game datasets to evaluate the proposed model. Extensive experiments show that our proposed model outperforms existing baseline models. Show less

Although various image-based domain adaptation (DA) techniques have been proposed in recent years, domain shift in videos is still not well-explored. Most previous works only evaluate performance on small-scale datasets which are saturated. Therefore, we first propose a larger-scale dataset with larger domain discrepancy: UCF-HMDB_full. Second, we investigate different DA integration methods for videos, and show that simultaneously aligning and learning temporal dynamics achieves effective… Show more

Although various image-based domain adaptation (DA) techniques have been proposed in recent years, domain shift in videos is still not well-explored. Most previous works only evaluate performance on small-scale datasets which are saturated. Therefore, we first propose a larger-scale dataset with larger domain discrepancy: UCF-HMDB_full. Second, we investigate different DA integration methods for videos, and show that simultaneously aligning and learning temporal dynamics achieves effective alignment even without sophisticated DA methods. Finally, we propose Temporal Attentive Adversarial Adaptation Network (TA3N), which explicitly attends to the temporal dynamics using domain discrepancy for more effective domain alignment, achieving state-of-the-art performance on three video DA datasets. The codes are released. Show less

[2023 EURASIP Best Paper Award for Image Communication Journal]
Recent two-stream deep Convolutional Neural Networks (ConvNets) have made significant progress in recognizing human actions in videos. Despite their success, methods extending the basic two-stream ConvNet have not systematically explored possible network architectures to further exploit spatiotemporal dynamics within video sequences. Further, such networks often use different baseline two-stream networks. Therefore, the… Show more

[2023 EURASIP Best Paper Award for Image Communication Journal]
Recent two-stream deep Convolutional Neural Networks (ConvNets) have made significant progress in recognizing human actions in videos. Despite their success, methods extending the basic two-stream ConvNet have not systematically explored possible network architectures to further exploit spatiotemporal dynamics within video sequences. Further, such networks often use different baseline two-stream networks. Therefore, the differences and the distinguishing factors between various methods using Recurrent Neural Networks (RNN) or convolutional networks on temporally-constructed feature vectors (Temporal-ConvNet) are unclear. In this work, we first demonstrate a strong baseline two-stream ConvNet using ResNet-101. We use this baseline to thoroughly examine the use of both RNNs and Temporal-ConvNets for extracting spatiotemporal information. Building upon our experimental results, we then propose and investigate two different networks to further integrate spatiotemporal information: 1) temporal segment RNN and 2) Inception-style Temporal-ConvNet. We demonstrate that using both RNNs (using LSTMs) and Temporal-ConvNets on spatiotemporal feature matrices are able to exploit spatiotemporal dynamics to improve the overall performance. However, each of these methods require proper care to achieve state-of-the-art performance; for example, LSTMs require pre-segmented data or else they cannot fully exploit temporal information. Our analysis identifies specific limitations for each method that could form the basis of future work. Our experimental results on UCF101 and HMDB51 datasets achieve state-of-the-art performances, 94.1% and 69.0%, respectively, without requiring extensive temporal augmentation. Show less

Pinhole-array-based hand-held light field cameras can be used to capture 4-dimensional light field data for different applications such as digital refocusing and depth estimation. Our previous experiences suggest the design of the pinhole array mask is very critical to the performance of the camera, and the selection of mask parameters could be very different between applications. In this paper, we derive equations for determining the parameters of pinhole masks. The proposed physically-based… Show more

Pinhole-array-based hand-held light field cameras can be used to capture 4-dimensional light field data for different applications such as digital refocusing and depth estimation. Our previous experiences suggest the design of the pinhole array mask is very critical to the performance of the camera, and the selection of mask parameters could be very different between applications. In this paper, we derive equations for determining the parameters of pinhole masks. The proposed physically-based model can be applied to cameras of different pixel sizes. The experimental results which match the proposed model are also provided at the end of this paper. Show less

Depth estimation is one of the new functions provided by hand-held light field cameras. However, the quality of depth estimation is very sensitive to noise, which is especially a problem for scenes under low light conditions. In this paper, we propose a depth estimation flow for light field data,
which can be fully-automated and no noise characteristics are required a priori. The results of Root Mean Square Error (RMSE) and Percentage of Bad Matching Pixels (PBM) show the effectiveness of… Show more

Depth estimation is one of the new functions provided by hand-held light field cameras. However, the quality of depth estimation is very sensitive to noise, which is especially a problem for scenes under low light conditions. In this paper, we propose a depth estimation flow for light field data,
which can be fully-automated and no noise characteristics are required a priori. The results of Root Mean Square Error (RMSE) and Percentage of Bad Matching Pixels (PBM) show the effectiveness of this iterative correlation-based depth estimation flow even with basic filtering functions. Show less

The recent advances in RGB-D cameras have allowed us to better solve increasingly complex computer vision tasks. However, modern RGB-D cameras are still restricted by the short effective distances. The limitation may make RGB-D cameras not online accessible in practice, and degrade their applicability. We propose an alternative scenario to address this problem, and illustrate it with the application to action recognition. We use Kinect to offline collect an auxiliary, multi-modal database, in… Show more

The recent advances in RGB-D cameras have allowed us to better solve increasingly complex computer vision tasks. However, modern RGB-D cameras are still restricted by the short effective distances. The limitation may make RGB-D cameras not online accessible in practice, and degrade their applicability. We propose an alternative scenario to address this problem, and illustrate it with the application to action recognition. We use Kinect to offline collect an auxiliary, multi-modal database, in which not only the RGB videos but also the depth maps and skeleton structures of actions of interest
are available. Our approach aims to enhance action recognition in RGB videos by leveraging the extra database. Specifically, it optimizes a feature transformation, by which the actions to be recognized can be concisely reconstructed by entries in the auxiliary database. In this way, the inter-database variations are adapted. More importantly, each action can be augmented with additional depth and skeleton images retrieved from the auxiliary database. The proposed approach has been evaluated on three benchmarks of action recognition. The promising results manifest that the augmented depth and skeleton features can lead to remarkable boost in recognition accuracy. Show less