Two-stage methods have dominated Human-Object Interaction (HOI) detection for several years. Recently, one-stage HOI detection methods have become popular. In this paper, we aim to explore the essential pros and cons of two-stage and one-stage method
s. With this as the goal, we find that conventional two-stage methods mainly suffer from positioning positive interactive human-object pairs, while one-stage methods are challenging to make an appropriate trade-off on multi-task learning, i.e., object detection, and interaction classification. Therefore, a core problem is how to take the essence and discard the dregs from the conventional two types of methods. To this end, we propose a novel one-stage framework with disentangling human-object detection and interaction classification in a cascade manner. In detail, we first design a human-object pair generator based on a state-of-the-art one-stage HOI detector by removing the interaction classification module or head and then design a relatively isolated interaction classifier to classify each human-object pair. Two cascade decoders in our proposed framework can focus on one specific task, detection or interaction classification. In terms of the specific implementation, we adopt a transformer-based HOI detector as our base model. The newly introduced disentangling paradigm outperforms existing methods by a large margin, with a significant relative mAP gain of 9.32% on HICO-Det.
In the context of electroencephalogram (EEG)-based driver drowsiness recognition, it is still a challenging task to design a calibration-free system, since there exists a significant variability of EEG signals among different subjects and recording s
essions. As deep learning has received much research attention in recent years, many efforts have been made to use deep learning methods for EEG signal recognition. However, existing works mostly treat deep learning models as blackbox classifiers, while what have been learned by the models and to which extent they are affected by the noise from EEG data are still underexplored. In this paper, we develop a novel convolutional neural network that can explain its decision by highlighting the local areas of the input sample that contain important information for the classification. The network has a compact structure for ease of interpretation and takes advantage of separable convolutions to process the EEG signals in a spatial-temporal sequence. Results show that the model achieves an average accuracy of 78.35% on 11 subjects for leave-one-out cross-subject drowsiness recognition, which is higher than the conventional baseline methods of 53.4%-72.68% and state-of-art deep learning methods of 63.90%-65.61%. Visualization results show that the model has learned to recognize biologically explainable features from EEG signals, e.g., Alpha spindles, as strong indicators of drowsiness across different subjects. In addition, we also explore reasons behind some wrongly classified samples and how the model is affected by artifacts and noise in the data. Our work illustrates a promising direction on using interpretable deep learning models to discover meaning patterns related to different mental states from complex EEG signals.
Driver drowsiness is one of main factors leading to road fatalities and hazards in the transportation industry. Electroencephalography (EEG) has been considered as one of the best physiological signals to detect drivers drowsy states, since it direct
ly measures neurophysiological activities in the brain. However, designing a calibration-free system for driver drowsiness detection with EEG is still a challenging task, as EEG suffers from serious mental and physical drifts across different subjects. In this paper, we propose a compact and interpretable Convolutional Neural Network (CNN) to discover shared EEG features across different subjects for driver drowsiness detection. We incorporate the Global Average Pooling (GAP) layer in the model structure, allowing the Class Activation Map (CAM) method to be used for localizing regions of the input signal that contribute most for classification. Results show that the proposed model can achieve an average accuracy of 73.22% on 11 subjects for 2-class cross-subject EEG signal classification, which is higher than conventional machine learning methods and other state-of-art deep learning methods. It is revealed by the visualization technique that the model has learned biologically explainable features, e.g., Alpha spindles and Theta burst, as evidence for the drowsy state. It is also interesting to see that the model uses artifacts that usually dominate the wakeful EEG, e.g., muscle artifacts and sensor drifts, to recognize the alert state. The proposed model illustrates a potential direction to use CNN models as a powerful tool to discover shared features related to different mental states across different subjects from EEG signals.
In this paper, we address the makeup transfer and removal tasks simultaneously, which aim to transfer the makeup from a reference image to a source image and remove the makeup from the with-makeup image respectively. Existing methods have achieved mu
ch advancement in constrained scenarios, but it is still very challenging for them to transfer makeup between images with large pose and expression differences, or handle makeup details like blush on cheeks or highlight on the nose. In addition, they are hardly able to control the degree of makeup during transferring or to transfer a specified part in the input face. In this work, we propose the PSGAN++, which is capable of performing both detail-preserving makeup transfer and effective makeup removal. For makeup transfer, PSGAN++ uses a Makeup Distill Network to extract makeup information, which is embedded into spatial-aware makeup matrices. We also devise an Attentive Makeup Morphing module that specifies how the makeup in the source image is morphed from the reference image, and a makeup detail loss to supervise the model within the selected makeup detail area. On the other hand, for makeup removal, PSGAN++ applies an Identity Distill Network to embed the identity information from with-makeup images into identity matrices. Finally, the obtained makeup/identity matrices are fed to a Style Transfer Network that is able to edit the feature maps to achieve makeup transfer or removal. To evaluate the effectiveness of our PSGAN++, we collect a Makeup Transfer In the Wild dataset that contains images with diverse poses and expressions and a Makeup Transfer High-Resolution dataset that contains high-resolution images. Experiments demonstrate that PSGAN++ not only achieves state-of-the-art results with fine makeup details even in cases of large pose/expression differences but also can perform partial or degree-controllable makeup transfer.
Vision and language understanding techniques have achieved remarkable progress, but currently it is still difficult to well handle problems involving very fine-grained details. For example, when the robot is told to bring me the book in the girls lef
t hand, most existing methods would fail if the girl holds one book respectively in her left and right hand. In this work, we introduce a new task named human-centric relation segmentation (HRS), as a fine-grained case of HOI-det. HRS aims to predict the relations between the human and surrounding entities and identify the relation-correlated human parts, which are represented as pixel-level masks. For the above exemplar case, our HRS task produces results in the form of relation triplets <girl [left hand], hold, book> and exacts segmentation masks of the book, with which the robot can easily accomplish the grabbing task. Correspondingly, we collect a new Person In Context (PIC) dataset for this new task, which contains 17,122 high-resolution images and densely annotated entity segmentation and relations, including 141 object categories, 23 relation categories and 25 semantic human parts. We also propose a Simultaneous Matching and Segmentation (SMS) framework as a solution to the HRS task. I Outputs of the three branches are fused to produce the final HRS results. Extensive experiments on PIC and V-COCO datasets show that the proposed SMS method outperforms baselines with the 36 FPS inference speed.
Given a natural language expression and an image/video, the goal of referring segmentation is to produce the pixel-level masks of the entities described by the subject of the expression. Previous approaches tackle this problem by implicit feature int
eraction and fusion between visual and linguistic modalities in a one-stage manner. However, human tends to solve the referring problem in a progressive manner based on informative words in the expression, i.e., first roughly locating candidate entities and then distinguishing the target one. In this paper, we propose a Cross-Modal Progressive Comprehension (CMPC) scheme to effectively mimic human behaviors and implement it as a CMPC-I (Image) module and a CMPC-V (Video) module to improve referring image and video segmentation models. For image data, our CMPC-I module first employs entity and attribute words to perceive all the related entities that might be considered by the expression. Then, the relational words are adopted to highlight the target entity as well as suppress other irrelevant ones by spatial graph reasoning. For video data, our CMPC-V module further exploits action words based on CMPC-I to highlight the correct entity matched with the action cues by temporal graph reasoning. In addition to the CMPC, we also introduce a simple yet effective Text-Guided Feature Exchange (TGFE) module to integrate the reasoned multimodal features corresponding to different levels in the visual backbone under the guidance of textual information. In this way, multi-level features can communicate with each other and be mutually refined based on the textual context. Combining CMPC-I or CMPC-V with TGFE can form our image or video version referring segmentation frameworks and our frameworks achieve new state-of-the-art performances on four referring image segmentation benchmarks and three referring video segmentation benchmarks respectively.
Language-queried video actor segmentation aims to predict the pixel-level mask of the actor which performs the actions described by a natural language query in the target frames. Existing methods adopt 3D CNNs over the video clip as a general encoder
to extract a mixed spatio-temporal feature for the target frame. Though 3D convolutions are amenable to recognizing which actor is performing the queried actions, it also inevitably introduces misaligned spatial information from adjacent frames, which confuses features of the target frame and yields inaccurate segmentation. Therefore, we propose a collaborative spatial-temporal encoder-decoder framework which contains a 3D temporal encoder over the video clip to recognize the queried actions, and a 2D spatial encoder over the target frame to accurately segment the queried actors. In the decoder, a Language-Guided Feature Selection (LGFS) module is proposed to flexibly integrate spatial and temporal features from the two encoders. We also propose a Cross-Modal Adaptive Modulation (CMAM) module to dynamically recombine spatial- and temporal-relevant linguistic features for multimodal feature interaction in each stage of the two encoders. Our method achieves new state-of-the-art performance on two popular benchmarks with less computational overhead than previous approaches.
Determining which image regions to concentrate on is critical for Human-Object Interaction (HOI) detection. Conventional HOI detectors focus on either detected human and object pairs or pre-defined interaction locations, which limits learning of the
effective features. In this paper, we reformulate HOI detection as an adaptive set prediction problem, with this novel formulation, we propose an Adaptive Set-based one-stage framework (AS-Net) with parallel instances and interaction branches. To attain this, we map a trainable interaction query set to an interaction prediction set with a transformer. Each query adaptively aggregates the interaction-relevant features from global contexts through multi-head co-attention. Besides, the training process is supervised adaptively by matching each ground truth with the interaction prediction. Furthermore, we design an effective instance-aware attention module to introduce instructive features from the instance branch into the interaction branch. Our method outperforms previous state-of-the-art methods without any extra human pose and language features on three challenging HOI detection datasets. Especially, we achieve over $31%$ relative improvement on a large-scale HICO-DET dataset. Code is available at https://github.com/yoyomimi/AS-Net.
To address the challenging task of instance-aware human part parsing, a new bottom-up regime is proposed to learn category-level human semantic segmentation as well as multi-person pose estimation in a joint and end-to-end manner. It is a compact, ef
ficient and powerful framework that exploits structural information over different human granularities and eases the difficulty of person partitioning. Specifically, a dense-to-sparse projection field, which allows explicitly associating dense human semantics with sparse keypoints, is learnt and progressively improved over the network feature pyramid for robustness. Then, the difficult pixel grouping problem is cast as an easier, multi-person joint assembling task. By formulating joint association as maximum-weight bipartite matching, a differentiable solution is developed to exploit projected gradient descent and Dykstras cyclic projection algorithm. This makes our method end-to-end trainable and allows back-propagating the grouping error to directly supervise multi-granularity human representation learning. This is distinguished from current bottom-up human parsers or pose estimators which require sophisticated post-processing or heuristic greedy algorithms. Experiments on three instance-aware human parsing datasets show that our model outperforms other bottom-up alternatives with much more efficient inference.
Video relation detection problem refers to the detection of the relationship between different objects in videos, such as spatial relationship and action relationship. In this paper, we present video relation detection with trajectory-aware multi-mod
al features to solve this task. Considering the complexity of doing visual relation detection in videos, we decompose this task into three sub-tasks: object detection, trajectory proposal and relation prediction. We use the state-of-the-art object detection method to ensure the accuracy of object trajectory detection and multi-modal feature representation to help the prediction of relation between objects. Our method won the first place on the video relation detection task of Video Relation Understanding Grand Challenge in ACM Multimedia 2020 with 11.74% mAP, which surpasses other methods by a large margin.
