15 accepted papers
Pre-trained vision language models have shown remarkable performance on visual recognition tasks, but they typically assume the availability of complete multimodal inputs during both training and inference. In real-world scenarios, however, modalities may be missing due to privacy constraints, colle…
Deep hashing has been widely used for large-scale approximate nearest neighbor search due to its storage and search efficiency. However, existing deep hashing methods predominantly rely on abundant training data, leaving the more challenging scenario of low-resource adaptation for deep hashing relat…
Convolutions with orthogonal input-output Jacobian matrix, i.e., orthogonal convolution, have recently attracted substantial attention. A convolution layer with an orthogonal Jacobian matrix is 1-Lipschitz in the 2-norm, making the output robust to the perturbation in input. Meanwhile, an orthog…
Existing multilingual video corpus moment retrieval (mVCMR) methods are mainly based on a two-stream structure. The visual stream utilizes the visual content in the video to estimate the query-visual similarity, and the subtitle stream exploits the query-subtitle similarity. The final query-video si…
Bilinear pooling has achieved excellent performance in fine-grained recognition tasks. Nevertheless, high-dimensional bilinear features suffer from over-fitting and inefficiency. To alleviate these issues, compact bilinear pooling (CBP) methods were developed to generate low-dimensional features. Al…
Recent pretrained vision-language models have achieved impressive performance on cross-modal retrieval tasks in English. Their success, however, heavily depends on the availability of many annotated image-caption datasets for pretraining, where the texts are not necessarily in English. Although we c…
Greedy coordinate descent (GCD) is an efficient optimization algorithm for a wide range of machine learning and data mining applications. GCD could be significantly faster than randomized coordinate descent (RCD) if they have similar per iteration cost. Nevertheless, in some cases, the greedy rule u…
Bilinear pooling has achieved an excellent performance in many computer vision tasks such as fine-grained classification, scene recognition and texture recognition. However, the high-dimension features from bilinear pooling can sometimes be inefficient and prone to over-fitting. Random Maclaurin (RM…
By exploiting the cross-modal attention, cross-BERT methods have achieved state-of-the-art accuracy in cross-modal retrieval. Nevertheless, the heavy text-image interactions in the cross-BERT model are prohibitively slow for large-scale retrieval. Late-interaction methods trade off retrieval accurac…
Bilinear pooling has achieved an impressive improvement in many computer vision tasks. Recent studies discover that matrix normalization is vital for improving the performance of bilinear pooling. Nevertheless, traditional matrix square-root or logarithm normalization methods need singular value dec…
Different from the fully-supervised action detection problem that is dependent on expensive frame-level annotations, weakly supervised action detection (WSAD) only needs video-level annotations, making it more practical for real-world applications. Existing WSAD methods detect action instances by sc…
View-based methods have achieved considerable success in $3$D object recognition tasks. Different from existing view-based methods pooling the view-wise features, we tackle this problem from the perspective of patches-to-patches similarity measurement. By exploiting the relationship between polynom…
Product quantization has been widely used in fast image retrieval due to its effectiveness of coding high-dimensional visual features. By extending the hard assignment to soft assignment, we make it feasible to incorporate the product quantization as a layer of a convolutional neural network and pro…
Most of current visual search systems focus on image-to-image (point-to-point) search such as image and object retrieval. Nevertheless, fast image-to-video (point-to-set) search is much less exploited. This paper tackles object instance search in videos, where efficient point-to-set matching is esse…
This paper tackles the problem of efficient and effective object instance search in videos. To effectively capture the relevance between a query and video frames and precisely localize the particular object, we leverage the object proposals to improve the quality of object instance search in videos.…