视听学习

Current audio-visual separation methods share a standard architecture design where an audio encoder-decoder network is fused with visual encoding features at the encoder bottleneck. This design confounds the learning of multi-modal feature encoding with robust sound decoding for audio separation. To generalize to a new instrument, one must fine-tune the entire visual and audio network for all musical instruments. We re-formulate the visual-sound separation task and propose Instruments as Queries (iQuery) with a flexible query expansion mechanism. Our approach ensures cross-modal consistency and cross-instrument disentanglement. We utilize "visually named" queries to initiate the learning of audio queries and use cross-modal attention to remove potential sound source interference at the estimated waveforms. To generalize to a new instrument or event class, drawing inspiration from the text-prompt design, we insert additional queries as audio prompts while freezing the attention mechanism. Experimental results on three benchmarks demonstrate that our iQuery improves audio-visual sound source separation performance. Code is available at https://github.com/JiabenChen/iQuery.

This paper deals with the problem of localizing objects in image and video datasets from visual exemplars. In particular, we focus on the challenging problem of egocentric visual query localization. We first identify grave implicit biases in current query-conditioned model design and visual query datasets. Then, we directly tackle such biases at both frame and object set levels. Concretely, our method solves these issues by expanding limited annotations and dynamically dropping object proposals during training. Additionally, we propose a novel transformer-based module that allows for object-proposal set context to be considered while incorporating query information. We name our module Conditioned Contextual Transformer or CocoFormer. Our experiments show that the proposed adaptations improve egocentric query detection, leading to a better visual query localization system in both 2D and 3D configurations. Thus, we are able to improve frame-level detection performance from 26.28% to 31.26% in AP, which correspondingly improves the VQ2D and VQ3D localization scores by significant margins. Our improved context-aware query object detector ranked first and second in the VQ2D and VQ3D tasks in the 2nd Ego4D challenge. In addition, we showcase the relevance of our proposed model in the Few-Shot Detection (FSD) task, where we also achieve SOTA results.

This paper deals with Audio-Visual Speech Recognition (AVSR) under multimodal input corruption situation where audio inputs and visual inputs are both corrupted, which is not well addressed in previous research directions. Previous studies have focused on how to complement the corrupted audio inputs with the clean visual inputs with the assumption of the availability of clean visual inputs. However, in real life, the clean visual inputs are not always accessible and can even be corrupted by occluded lip region or with noises. Thus, we firstly analyze that the previous AVSR models are not indeed robust to the corruption of multimodal input streams, the audio and the visual inputs, compared to uni-modal models. Then, we design multimodal input corruption modeling to develop robust AVSR models. Lastly, we propose a novel AVSR framework, namely Audio-Visual Reliability Scoring module (AV-RelScore), that is robust to the corrupted multimodal inputs. The AV-RelScore can determine which input modal stream is reliable or not for the prediction and also can exploit the more reliable streams in prediction. The effectiveness of the proposed method is evaluated with comprehensive experiments on popular benchmark databases, LRS2 and LRS3. We also show that the reliability scores obtained by AV-RelScore well reflect the degree of corruption and make the proposed model focus on the reliable multimodal representations.

Humans have the ability of recognizing visual semantics in an unlimited granularity, but existing visual recognition algorithms cannot achieve this goal. In this paper, we establish a new paradigm named visual recognition by request (ViRReq) to bridge the gap. The key lies in decomposing visual recognition into atomic tasks named requests and leveraging a knowledge base, a hierarchical and text-based dictionary, to assist task definition. ViRReq allows for (i) learning complicated whole-part hierarchies from highly incomplete annotations and (ii) inserting new concepts with minimal efforts. We also establish a solid baseline by integrating language-driven recognition into recent semantic and instance segmentation methods, and demonstrate its flexible recognition ability on CPP and ADE20K, two datasets with hierarchical whole-part annotations.

Visible-modal object tracking gives rise to a series of downstream multi-modal tracking tributaries. To inherit the powerful representations of the foundation model, a natural modus operandi for multi-modal tracking is full fine-tuning on the RGB-based parameters. Albeit effective, this manner is not optimal due to the scarcity of downstream data and poor transferability, etc. In this paper, inspired by the recent success of the prompt learning in language models, we develop Visual Prompt multi-modal Tracking (ViPT), which learns the modal-relevant prompts to adapt the frozen pre-trained foundation model to various downstream multimodal tracking tasks. ViPT finds a better way to stimulate the knowledge of the RGB-based model that is pre-trained at scale, meanwhile only introducing a few trainable parameters (less than 1% of model parameters). ViPT outperforms the full fine-tuning paradigm on multiple downstream tracking tasks including RGB+Depth, RGB+Thermal, and RGB+Event tracking. Extensive experiments show the potential of visual prompt learning for multi-modal tracking, and ViPT can achieve state-of-the-art performance while satisfying parameter efficiency. Code and models are available at https://github.com/jiawen-zhu/ViPT.

Visual localization is a core component in many applications, including augmented reality (AR). Localization algorithms compute the camera pose of a query image w.r.t. a scene representation, which is typically built from images. This often requires capturing and storing large amounts of data, followed by running Structure-from-Motion (SfM) algorithms. An interesting, and underexplored, source of data for building scene representations are 3D models that are readily available on the Internet, e.g., hand-drawn CAD models, 3D models generated from building footprints, or from aerial images. These models allow to perform visual localization right away without the time-consuming scene capturing and model building steps. Yet, it also comes with challenges as the available 3D models are often imperfect reflections of reality. E.g., the models might only have generic or no textures at all, might only provide a simple approximation of the scene geometry, or might be stretched. This paper studies how the imperfections of these models affect localization accuracy. We create a new benchmark for this task and provide a detailed experimental evaluation based on multiple 3D models per scene. We show that 3D models from the Internet show promise as an easy-to-obtain scene representation. At the same time, there is significant room for improvement for visual localization pipelines. To foster research on this interesting and challenging task, we release our benchmark at v-pnk.github.io/cadloc.

Humans possess a versatile mechanism for extracting structured representations of our visual world. When looking at an image, we can decompose the scene into entities and their parts as well as obtain the dependencies between them. To mimic such capability, we propose Visual Dependency Transformers (DependencyViT) that can induce visual dependencies without any labels. We achieve that with a novel neural operator called reversed attention that can naturally capture long-range visual dependencies between image patches. Specifically, we formulate it as a dependency graph where a child token in reversed attention is trained to attend to its parent tokens and send information following a normalized probability distribution rather than gathering information in conventional self-attention. With such a design, hierarchies naturally emerge from reversed attention layers, and a dependency tree is progressively induced from leaf nodes to the root node unsupervisedly. DependencyViT offers several appealing benefits. (i) Entities and their parts in an image are represented by different subtrees, enabling part partitioning from dependencies; (ii) Dynamic visual pooling is made possible. The leaf nodes which rarely send messages can be pruned without hindering the model performance, based on which we propose the lightweight DependencyViT-Lite to reduce the computational and memory footprints; (iii) DependencyViT works well on both self- and weakly-supervised pretraining paradigms on ImageNet, and demonstrates its effectiveness on 8 datasets and 5 tasks, such as unsupervised part and saliency segmentation, recognition, and detection.

Vision transformers (ViTs) have achieved impressive results on various computer vision tasks in the last several years. In this work, we study the capability of frozen ViTs, pretrained only on visual data, to generalize to audio-visual data without finetuning any of its original parameters. To do so, we propose a latent audio-visual hybrid (LAVISH) adapter that adapts pretrained ViTs to audio-visual tasks by injecting a small number of trainable parameters into every layer of a frozen ViT. To efficiently fuse visual and audio cues, our LAVISH adapter uses a small set of latent tokens, which form an attention bottleneck, thus, eliminating the quadratic cost of standard cross-attention. Compared to the existing modality-specific audio-visual methods, our approach achieves competitive or even better performance on various audio-visual tasks while using fewer tunable parameters and without relying on costly audio pretraining or external audio encoders. Our code is available at https://genjib.github.io/project_page/LAVISH/

Existing Siamese tracking methods, which are built on pair-wise matching between two single frames, heavily rely on additional sophisticated mechanism to exploit temporal information among successive video frames, hindering them from high efficiency and industrial deployments. In this work, we resort to sequence-level target matching that can encode temporal contexts into the spatial features through a neat feedforward video model. Specifically, we adapt the standard video transformer architecture to visual tracking by enabling spatiotemporal feature learning directly from frame-level patch sequences. To better adapt to the tracking task, we carefully blend the spatiotemporal information in the video clips through sequential multi-branch triplet blocks, which formulates a video transformer backbone. Our experimental study compares different model variants, such as tokenization strategies, hierarchical structures, and video attention schemes. Then, we propose a disentangled dual-template mechanism that decouples static and dynamic appearance changes over time, and reduces the temporal redundancy in video frames. Extensive experiments show that our method, named as VideoTrack, achieves state-of-the-art results while running in real-time.

In this work, we introduce Vid2Seq, a multi-modal single-stage dense event captioning model pretrained on narrated videos which are readily-available at scale. The Vid2Seq architecture augments a language model with special time tokens, allowing it to seamlessly predict event boundaries and textual descriptions in the same output sequence. Such a unified model requires large-scale training data, which is not available in current annotated datasets. We show that it is possible to leverage unlabeled narrated videos for dense video captioning, by reformulating sentence boundaries of transcribed speech as pseudo event boundaries, and using the transcribed speech sentences as pseudo event captions. The resulting Vid2Seq model pretrained on the YT-Temporal-1B dataset improves the state of the art on a variety of dense video captioning benchmarks including YouCook2, ViTT and ActivityNet Captions. Vid2Seq also generalizes well to the tasks of video paragraph captioning and video clip captioning, and to few-shot settings. Our code is publicly available at https://antoyang.github.io/vid2seq.html.

Dominant pre-training works for image-text retrieval adopt "dual-encoder" architecture to enable high efficiency, where two encoders are used to extract image and text representations and contrastive learning is employed for global alignment. However, coarse-grained global alignment ignores detailed semantic associations between image and text. In this work, we propose a novel proxy task, named Visual-Language Error Modeling (ViLEM), to inject detailed image-text association into "dual-encoder" model by "proofreading" each word in the text against the corresponding image. Specifically, we first edit the image-paired text to automatically generate diverse plausible negative texts with pre-trained language models. ViLEM then enforces the model to discriminate the correctness of each word in the plausible negative texts and further correct the wrong words via resorting to image information. Furthermore, we propose a multi-granularity interaction framework to perform ViLEM via interacting text features with both global and local image features, which associates local text semantics with both high-level visual context and multi-level local visual information. Our method surpasses state-of-the-art "dual-encoder" methods by a large margin on the image-text retrieval task and significantly improves discriminativeness to local textual semantics. Our model can also generalize well to video-text retrieval.

Research on continual learning has recently led to a variety of work in unimodal community, however little attention has been paid to multimodal tasks like visual question answering (VQA). In this paper, we establish a novel VQA Continual Learning setting named VQACL, which contains two key components: a dual-level task sequence where visual and linguistic data are nested, and a novel composition testing containing new skill-concept combinations. The former devotes to simulating the ever-changing multimodal datastream in real world and the latter aims at measuring models' generalizability for cognitive reasoning. Based on our VQACL, we perform in-depth evaluations of five well-established continual learning methods, and observe that they suffer from catastrophic forgetting and have weak generalizability. To address above issues, we propose a novel representation learning method, which leverages a sample-specific and a sample-invariant feature to learn representations that are both discriminative and generalizable for VQA. Furthermore, by respectively extracting such representation for visual and textual input, our method can explicitly disentangle the skill and concept. Extensive experimental results illustrate that our method significantly outperforms existing models, demonstrating the effectiveness and compositionality of the proposed approach.

The correlation between the vision and text is essential for video moment retrieval (VMR), however, existing methods heavily rely on separate pre-training feature extractors for visual and textual understanding. Without sufficient temporal boundary annotations, it is non-trivial to learn universal video-text alignments. In this work, we explore multi-modal correlations derived from large-scale image-text data to facilitate generalisable VMR. To address the limitations of image-text pre-training models on capturing the video changes, we propose a generic method, referred to as Visual-Dynamic Injection (VDI), to empower the model's understanding of video moments. Whilst existing VMR methods are focusing on building temporal-aware video features, being aware of the text descriptions about the temporal changes is also critical but originally overlooked in pre-training by matching static images with sentences. Therefore, we extract visual context and spatial dynamic information from video frames and explicitly enforce their alignments with the phrases describing video changes (e.g. verb). By doing so, the potentially relevant visual and motion patterns in videos are encoded in the corresponding text embeddings (injected) so to enable more accurate video-text alignments. We conduct extensive experiments on two VMR benchmark datasets (Charades-STA and ActivityNet-Captions) and achieve state-of-the-art performances. Especially, VDI yields notable advantages when being tested on the out-of-distribution splits where the testing samples involve novel scenes and vocabulary.

Under partial-label learning (PLL) where, for each training instance, only a set of ambiguous candidate labels containing the unknown true label is accessible, contrastive learning has recently boosted the performance of PLL on vision tasks, attributed to representations learned by contrasting the same/different classes of entities. Without access to true labels, positive points are predicted using pseudolabels that are inherently noisy, and negative points often require large batches or momentum encoders, resulting in unreliable similarity information and a high computational overhead. In this paper, we rethink a state-of-the-art contrastive PLL method PiCO [24], inspiring the design of a simple framework termed PaPi (Partial-label learning with a guided Prototypical classifier), which demonstrates significant scope for improvement in representation learning, thus contributing to label disambiguation. PaPi guides the optimization of a prototypical classifier by a linear classifier with which they share the same feature encoder, thus explicitly encouraging the representation to reflect visual similarity between categories. It is also technically appealing, as PaPi requires only a few components in PiCO with the opposite direction of guidance, and directly eliminates the contrastive learning module that would introduce noise and consume computational resources. We empirically demonstrate that PaPi significantly outperforms other PLL methods on various image classification tasks.

Current attention algorithms (e.g., self-attention) are stimulus-driven and highlight all the salient objects in an image. However, intelligent agents like humans often guide their attention based on the high-level task at hand, focusing only on task-related objects. This ability of task-guided top-down attention provides task-adaptive representation and helps the model generalize to various tasks. In this paper, we consider top-down attention from a classic Analysis-by-Synthesis (AbS) perspective of vision. Prior work indicates a functional equivalence between visual attention and sparse reconstruction; we show that an AbS visual system that optimizes a similar sparse reconstruction objective modulated by a goal-directed top-down signal naturally simulates top-down attention. We further propose Analysis-by-Synthesis Vision Transformer (AbSViT), which is a top-down modulated ViT model that variationally approximates AbS, and achieves controllable top-down attention. For real-world applications, AbSViT consistently improves over baselines on Vision-Language tasks such as VQA and zero-shot retrieval where language guides the top-down attention. AbSViT can also serve as a general backbone, improving performance on classification, semantic segmentation, and model robustness. Project page: https://sites.google.com/view/absvit.

Learning with large-scale unlabeled data has become a powerful tool for pre-training Visual Transformers (VTs). However, prior works tend to overlook that, in real-world scenarios, the input data may be corrupted and unreliable. Pre-training VTs on such corrupted data can be challenging, especially when we pre-train via the masked autoencoding approach, where both the inputs and masked "ground truth" targets can potentially be unreliable in this case. To address this limitation, we introduce the Token Boosting Module (TBM) as a plug-and-play component for VTs that effectively allows the VT to learn to extract clean and robust features during masked autoencoding pre-training. We provide theoretical analysis to show how TBM improves model pre-training with more robust and generalizable representations, thus benefiting downstream tasks. We conduct extensive experiments to analyze TBM's effectiveness, and results on four corrupted datasets demonstrate that TBM consistently improves performance on downstream tasks.

In this paper, we study the problem of temporal video grounding (TVG), which aims to predict the starting/ending time points of moments described by a text sentence within a long untrimmed video. Benefiting from fine-grained 3D visual features, the TVG techniques have achieved remarkable progress in recent years. However, the high complexity of 3D convolutional neural networks (CNNs) makes extracting dense 3D visual features time-consuming, which calls for intensive memory and computing resources. Towards efficient TVG, we propose a novel text-visual prompting (TVP) framework, which incorporates optimized perturbation patterns (that we call 'prompts') into both visual inputs and textual features of a TVG model. In sharp contrast to 3D CNNs, we show that TVP allows us to effectively co-train vision encoder and language encoder in a 2D TVG model and improves the performance of crossmodal feature fusion using only low-complexity sparse 2D visual features. Further, we propose a Temporal-Distance IoU (TDIoU) loss for efficient learning of TVG. Experiments on two benchmark datasets, Charades-STA and ActivityNet Captions datasets, empirically show that the proposed TVP significantly boosts the performance of 2D TVG (e.g., 9.79% improvement on Charades-STA and 30.77% improvement on ActivityNet Captions) and achieves 5x inference acceleration over TVG using 3D visual features. Codes are available at Open.Intel.

Recently reported state-of-the-art results in visual speech recognition (VSR) often rely on increasingly large amounts of video data, while the publicly available transcribed video datasets are limited in size. In this paper, for the first time, we study the potential of leveraging synthetic visual data for VSR. Our method, termed SynthVSR, substantially improves the performance of VSR systems with synthetic lip movements. The key idea behind SynthVSR is to leverage a speech-driven lip animation model that generates lip movements conditioned on the input speech. The speech-driven lip animation model is trained on an unlabeled audio-visual dataset and could be further optimized towards a pre-trained VSR model when labeled videos are available. As plenty of transcribed acoustic data and face images are available, we are able to generate large-scale synthetic data using the proposed lip animation model for semi-supervised VSR training. We evaluate the performance of our approach on the largest public VSR benchmark - Lip Reading Sentences 3 (LRS3). SynthVSR achieves a WER of 43.3% with only 30 hours of real labeled data, outperforming off-the-shelf approaches using thousands of hours of video. The WER is further reduced to 27.9% when using all 438 hours of labeled data from LRS3, which is on par with the state-of-the-art self-supervised AV-HuBERT method. Furthermore, when combined with large-scale pseudo-labeled audio-visual data SynthVSR yields a new state-of-the-art VSR WER of 16.9% using publicly available data only, surpassing the recent state-of-the-art approaches trained with 29 times more non-public machine-transcribed video data (90,000 hours). Finally, we perform extensive ablation studies to understand the effect of each component in our proposed method.

Visual place recognition (VPR) is usually considered as a specific image retrieval problem. Limited by existing training frameworks, most deep learning-based works cannot extract sufficiently stable global features from RGB images and rely on a time-consuming re-ranking step to exploit spatial structural information for better performance. In this paper, we propose StructVPR, a novel training architecture for VPR, to enhance structural knowledge in RGB global features and thus improve feature stability in a constantly changing environment. Specifically, StructVPR uses segmentation images as a more definitive source of structural knowledge input into a CNN network and applies knowledge distillation to avoid online segmentation and inference of seg-branch in testing. Considering that not all samples contain high-quality and helpful knowledge, and some even hurt the performance of distillation, we partition samples and weigh each sample's distillation loss to enhance the expected knowledge precisely. Finally, StructVPR achieves impressive performance on several benchmarks using only global retrieval and even outperforms many two-stage approaches by a large margin. After adding additional re-ranking, ours achieves state-of-the-art performance while maintaining a low computational cost.