In this paper, we propose an online movement-specific vehicle counting system to realize robust traffic flow analysis at crowded intersections. Our proposed framework adopts PP-YOLO as the vehicle detector and adapts ...
详细信息
ISBN:
(纸本)9781665448994
In this paper, we propose an online movement-specific vehicle counting system to realize robust traffic flow analysis at crowded intersections. Our proposed framework adopts PP-YOLO as the vehicle detector and adapts the Deep-Sort algorithm to perform multi-object tracking. In order to realize online and robust vehicle counting, we further adopt a shape-based movement assignment strategy to differentiate movements and carefully designed spatial constraints to effectively reduce false-positive counts. Our proposed framework achieves the overall S1-score of 0.9467, ranking the first in the AICITY2021-track1 challenge.
Previous research on localizing a target region in an image referred to by a natural language expression has occurred within an object-centric paradigm. However, in practice, there may not be any easily named or ident...
详细信息
ISBN:
(纸本)9781728193601
Previous research on localizing a target region in an image referred to by a natural language expression has occurred within an object-centric paradigm. However, in practice, there may not be any easily named or identifiable objects near a target location. Instead, references may need to rely on basic visual attributes, such as color or geometric clues. An expression like "a red something beside a blue vertical line" could still pinpoint a target location. As such, we begin to explore the open challenge of computational object-agnostic reference by constructing a novel dataset and by devising a new set of algorithms that can identify a target region in an image when given a referring expression containing only basic conceptual features.
Lossy image compression causes a loss of texture, especially at low bitrate. To mitigate this problem, we propose a novel image compression method that utilizes a reference-based image super-resolution model. We use t...
详细信息
ISBN:
(纸本)9781665448994
Lossy image compression causes a loss of texture, especially at low bitrate. To mitigate this problem, we propose a novel image compression method that utilizes a reference-based image super-resolution model. We use two image compression models and a self texture transfer model. The image compression models encode and decode a whole input image and selected reference patches. The reference patches are small but compressed with high quality. The self texture transfer model transfers the texture of reference patches into similar regions in the compressed image. The experimental results show that our method can reconstruct accurate texture by transferring the texture of reference patches.
We propose a learning-based image compression method that achieves any arbitrary input bitrate via user-guided bit allocation to preferred regions. We verify our hypothesis of incorporating user guidance for bitrate c...
详细信息
ISBN:
(数字)9781665487399
ISBN:
(纸本)9781665487399
We propose a learning-based image compression method that achieves any arbitrary input bitrate via user-guided bit allocation to preferred regions. We verify our hypothesis of incorporating user guidance for bitrate control by experimenting with alternatives that do not have any guidance. We conduct extensive evaluation on CelebA-HQ and CityScapes dataset using standard quantitative metrics and human studies showing that our single model for multiple bitrates achieves similar or better performance as compared to previous learned image compression methods that require re-training for each new bitrate.
Recent work such as StyleCLIP aims to harness the power of CLIP embeddings for controlled manipulations. Although these models are capable of manipulating images based on a text prompt, the success of the manipulation...
详细信息
ISBN:
(数字)9781665487399
ISBN:
(纸本)9781665487399
Recent work such as StyleCLIP aims to harness the power of CLIP embeddings for controlled manipulations. Although these models are capable of manipulating images based on a text prompt, the success of the manipulation often depends on careful selection of the appropriate text for the desired manipulation. This limitation makes it particularly difficult to perform text-based manipulations in domains where the user lacks expertise, such as fashion. To address this problem, we propose a method for automatically determining the most successful and relevant text-based edits using a pre-trained StyleGAN model. Our approach consists of a novel mechanism that uses CLIP to guide beam-search decoding, and a ranking method that identifies the most relevant and successful edits based on a list of keywords. We also demonstrate the capabilities of our framework in several domains, including fashion.
We tackle here a specific, still not widely addressed aspect, of AI robustness, which consists of seeking invariance / insensitivity of model performance to hidden factors of variations in the data. Towards this end, ...
详细信息
ISBN:
(数字)9781665487399
ISBN:
(纸本)9781665487399
We tackle here a specific, still not widely addressed aspect, of AI robustness, which consists of seeking invariance / insensitivity of model performance to hidden factors of variations in the data. Towards this end, we employ a two step strategy that a) does unsupervised discovery, via generative models, of sensitive factors that cause models to under-perform, and b) intervenes models to make their performance invariant to these sensitive factors' influence. We consider 3 separate interventions for robustness, including: data augmentation, semantic consistency, and adversarial alignment. We evaluate our method using metrics that measure trade offs between invariance (insensitivity) and overall performance (utility) and show the benefits of our method for 3 settings (unsupervised, semi-supervised and generalization).
In this paper we present a unified formulation for a large class of relative pose problems with radial distortion and varying calibration. For minimal cases, we show that one can eliminate the number of parameters dow...
详细信息
ISBN:
(纸本)9781665448994
In this paper we present a unified formulation for a large class of relative pose problems with radial distortion and varying calibration. For minimal cases, we show that one can eliminate the number of parameters down to one to three. The relative pose can then be expressed using varying calibration constraints on the fundamental matrix, with entries that are polynomial in the parameters. We can then apply standard techniques based on the action matrix and Sturm sequences to construct our solvers. This enables efficient solvers for a large class of relative pose problems with radial distortion, using a common framework. We evaluate a number of these solvers for robust two-view inlier and epipolar geometry estimation, used as minimal solvers in RANSAC.
We present an end-to-end system for learning outfit recommendations. The core problem we address is how a customer can receive clothing/accessory recommendations based on a current outfit and what type of item the cus...
详细信息
ISBN:
(纸本)9781665448994
We present an end-to-end system for learning outfit recommendations. The core problem we address is how a customer can receive clothing/accessory recommendations based on a current outfit and what type of item the customer wishes to add to the outfit. Using a repository of coherent and stylish outfits, we leverage self-attention to learn a mapping from the current outfit and the customer-requested category to a visual descriptor output. This output is then fed into nearest-neighbor-based visual search, which, during training, is learned via triplet loss and mini-batch retrievals. At inference time, we use a beam search with a desired outfit composition to generate outfits at scale. Moreover, the attention networks provide a diagnostic look into the recommendation process, serving as a fashion-based sanity check.
Event-based vision, as realized by bio-inspired Dynamic vision Sensors (DVS), is gaining more and more popularity due to its advantages of high temporal resolution, wide dynamic range and power efficiency at the same ...
详细信息
ISBN:
(纸本)9781538607336
Event-based vision, as realized by bio-inspired Dynamic vision Sensors (DVS), is gaining more and more popularity due to its advantages of high temporal resolution, wide dynamic range and power efficiency at the same time. Potential applications include surveillance, robotics, and autonomous navigation under uncontrolled environment conditions. In this paper, we deal with event-based vision for 3D reconstruction of dynamic scene content by using two stationary DVS in a stereo configuration. We focus on a cooperative stereo approach and suggest an improvement over a previously published algorithm that reduces the measured mean error by over 50 percent. An available ground truth data set for stereo event data is utilized to analyze the algorithm's sensitivity to parameter variation and for comparison with competing techniques.
Several recent efforts in computervision indicate a trend toward studying and understanding problems in larger scale environments, beyond single images, and focus on connections to tasks in navigation, mobile manipul...
详细信息
ISBN:
(数字)9781538661000
ISBN:
(纸本)9781538661000
Several recent efforts in computervision indicate a trend toward studying and understanding problems in larger scale environments, beyond single images, and focus on connections to tasks in navigation, mobile manipulation, and visual question answering. A common goal of these tasks is the capability of moving in the environment, acquiring novel views during perception and while performing a task. This capability comes easily in synthetic environments, however achieving the same effect with real images is much more laborious. We propose using the existing Active vision Dataset to form a benchmark for such problems in a real-world settings with real images. The dataset is well suited for evaluating tasks of multiview active recognition, target driven navigation, and target search, and also can be effective for studying the transfer of strategies learned in simulation to real settings.
暂无评论