29 accepted papers
Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires an agent to follow language instructions to reach a target in unseen, 3D environments. A powerful VLN-CE agent requires two crucial abilities during cross-modal planning: spatial reasoning to explore towards the target locat
Safe and feasible trajectory planning is critical for real-world autonomous driving systems. However, existing learning-based planners rely heavily on expert demonstrations, which not only lack explicit safety awareness but also risk inheriting undesirable behaviors such as speeding from suboptimal…
Planning the trajectory for an autonomous vehicle (AV) requires considering both the AV's objectives and the behaviors of surrounding agents, which interact in a dynamic process. Joint prediction and planning (JPP) methods have been proposed to model this bidirectional interaction and generate compa
Large vision-language models (LVLMs) are highly vulnerable to visual corruptions, substantially compromising their reliability and limiting real-world deployment. Prior work has attributed this degradation primarily to insufficient visual grounding and overreliance on language priors. However, these
Diffusion models have shown impressive performance in generative tasks, demonstrating their ability to capture detailed structural and semantic information. Recently, these capabilities have been extended to visual understanding, with studies employing diffusion models as the backbone for various pe
Guiding visually impaired individuals (VI) walking along planned paths is essential for enabling independent long-distance mobility. Current reactive approaches only correct deviations after they occur. These methods ignore VI's walking dynamics (e.g., reaction latency and heading drift), resulting
Multimodal Large Language Models (MLLMs) have made significant strides in visual and language tasks. However, despite their impressive performance on standard datasets, these models encounter considerable robustness challenges when processing corrupted images, raising concerns about their reliabilit…
Robots rely heavily on visual perception to understand and interact with complex environments. To support this capability, modern perception models have become increasingly large and powerful, resulting in high computational costs that hinder their real-time performance in robotic applications. Exis
Vision Transformers (ViTs) are now flourishing in the computer vision area. Despite the remarkable success, ViTs suffer from high computational costs, which greatly hinder their practical usage. Token reduction, which identifies and discards unimportant tokens during forward propagation, has then be…
Predicting the trajectories of road agents is essential for autonomous driving systems. The recent mainstream methods follow a static paradigm which predicts the future trajectory by using a fixed duration of historical frames. These methods make the predictions independently even at adjacent time s…
"The recent technique of Model-Based Reinforcement Learning learns to make decisions by building a world model about the dynamics of the environment. The world model learning requires extensive interactions with the real environment. Therefore, several innovative approaches such as APV proposed to u…
Domain generalization (DG) attempts to learn a model on source domains that can well generalize to unseen but different domains. The multiple source domains are innately different in distribution but intrinsically related to each other, e.g., from the same label space. To achieve a generalizable fea…
Feature distillation makes the student mimic the intermediate features of the teacher. Nearly all existing feature-distillation methods use L2 distance or its slight variants as the distance metric between teacher and student features. However, while L2 distance is isotropic w.r.t. all dimensions, t…
"Hair editing is an essential but challenging task in portrait editing considering the complex geometry and material of hair. Existing methods have achieved promising results by editing through a reference photo, user-painted mask, or guiding strokes. However, when a user provides no reference photo…
Recent studies on Generative Adversarial Network (GAN) reveal that different layers of a generative CNN hold different semantics of the synthesized images. However, few GAN models have explicit dimensions to control the semantic attributes represented in a specific layer. This paper proposes EigenGA…
Image-level weakly supervised semantic segmentation is a challenging problem that has been deeply studied in recent years. Most of advanced solutions exploit class activation map (CAM). However, CAMs can hardly serve as the object mask due to the gap between full and weak supervisions. In this paper…
Domain adaptation attempts to boost the performance on a target domain by borrowing knowledge from a well established source domain. To handle the distribution gap between two domains, the prominent approaches endeavor to extract domain-invariant features. It is known that after a perfect domain ali…
Benefitted from its great success on many tasks, deep learning is increasingly used on low-computational-cost devices, e.g. smartphone, embedded devices, etc. To reduce the high computational and memory cost, in this work, we propose a fully learnable group convolution module (FLGC for short) which…
Generally, we human follow the roughly common aging trends, e.g., the wrinkles only tend to be more, longer or deeper. However, the aging process of each individual is more dominated by his/her personalized factors, including the invariant factors such as identity and mole, as well as the personaliz…
Weakly supervised object detection aims at learning precise object detectors, given image category labels. In recent prevailing works, this problem is generally formulated as a multiple instance learning module guided by an image classification loss. The object bounding box is assumed to be the one…
Domain adaptation attempts to transfer the knowledge obtained from the source domain to the target domain, i.e., the domain where the testing data are. The main challenge lies in the distribution discrepancy between source and target domain. Most existing works endeavor to learn domain invariant rep…
In current face recognition approaches with convolutional neural network (CNN), a pair of faces to compare are independently fed into the CNN for feature extraction. For both faces the same kernels are applied and hence the representation of a face stays fixed regardless of who it is compared with.…
Face attribute editing aims at editing the face image with the given attribute. Most existing works employ Generative Adversarial Network (GAN) to operate face attribute editing. However, these methods inevitably change the attribute-irrelevant regions, as shown in Fig.~ ef{fig1}. Therefore, we intr…
Rotation-invariant face detection, i.e. detecting faces with arbitrary rotation-in-plane (RIP) angles, is widely required in unconstrained applications but still remains as a challenging task, due to the large variations of face appearances. Most existing methods compromise with speed or accuracy to…
Convolutional Neural Network (CNN) has led to significant progress in face recognition. Currently most CNN-based face recognition methods follow a two-step pipeline, i.e. a detected face is first aligned to a canonical one pre-defined by a mean face shape, and then it is fed into a CNN to extract fe…
Cross-view recognition that intends to classify samples between different views is an important problem in computer vision. The large discrepancy between different even heterogenous views make this problem quite challenging. To eliminate the complex (maybe even highly nonlinear) view discrepancy for…
Face alignment or facial landmark detection plays an important role in many computer vision applications, e.g., face recognition, facial expression recognition, face animation, etc. However, the performance of face alignment system degenerates severely when occlusions occur. In this work, we propose…
In many real-world applications, the domain of model learning (referred as source domain) is usually inconsistent with or even different from the domain of testing (referred as target domain), which makes the learnt model degenerate in target domain, i.e., the test domain. To alleviate the discrepan…
Facial landmark detection, as a vital topic in computer vision, has been studied for many decades and lots of datasets have been collected for evaluation. These datasets usually have different annotations, e.g., 68-landmark markup for LFPW dataset, while 74-landmark markup for GTAV dataset. Intuitiv…