Recent contrastive multimodal vision-language models like CLIP have demonstrated robust open-world semantic understanding, becoming the standard image backbones for vision-language applications. However, recent findings suggest high semantic similarity between well-trained unimodal encoders, which raises a key question: Is there a plausible way to connect unimodal backbones for vision-language tasks? To this end, we propose a novel framework that aligns vision and language using frozen unimodal encoders. It involves selecting semantically similar encoders in the latent space, curating a concept-rich dataset of image-caption pairs, and training simple MLP projectors. We evaluated our approach on 12 zero-shot classification datasets and 2 image-text retrieval datasets. Our best model, utilizing DINOv2 and All-Roberta-Large text encoder, achieves 76% accuracy on ImageNet with a 20-fold reduction in data and 65-fold reduction in compute requirements compared multi-modal alignment where models are trained from scratch. The proposed framework enhances the accessibility of multimodal model development while enabling flexible adaptation across diverse scenarios. Code and curated datasets are available at github.com/mayug/freeze-align.

We present Saliency Benchmark (SalBench), a novel benchmark designed to assess the capability of Large Vision-Language Models (LVLM) in detecting visually salient features that are readily apparent to humans, such as a large circle amidst a grid of smaller ones. This benchmark focuses on low-level features including color, intensity, and orientation, which are fundamental to human visual processing. Our SalBench consists of images that highlight rare, unusual, or unexpected elements within scenes, and naturally draw human attention. It comprises three novel tasks for evaluating the perceptual capabilities of LVLM: Odd-One-Out Detection, Referring Odd-One-Out, and Visual Referring Odd-One-Out. We perform a comprehensive evaluation of state-of-the-art LVLM using SalBench and our findings reveal a surprising limitation: LVLM struggle to identify seemingly obvious visual anomalies, with even the advanced GPT-4o achieving only 47.6\% accuracy on such a simple task. SalBench will be an important step in measuring the capabilities of LVLM that align with the subtle definition of human attention.

Aligned text-image encoders such as CLIP have become the de-facto model for vision-language tasks. Further-more, modality-specific encoders achieve impressive per-formances in their respective domains. This raises a cen-tral question: does an alignment exist between uni-modal vision and language encoders since they fundamentally rep-resent the same physical world? Analyzing the latent spaces structure of vision and language models on image-caption benchmarks using the Centered Kernel Alignment (CKA), we find that the representation spaces of unaligned and aligned encoders are semantically similar. In the absence of statistical similarity in aligned encoders like CLIP, we show that a possible matching of unaligned encoders exists with-out any training. We frame this as a seeded graph-matching problem exploiting the semantic similarity between graphs and propose two methods - a Fast Quadratic Assignment Problem optimization, and a novel localized CKA metric-based matching/retrieval. We demonstrate the effectiveness of this on several downstream tasks including cross-lingual, cross-domain caption matching and image classification. Code available at github.com/mayug/0-shot-llm-vision.

The Lip Reading Sentences-3 (LRS3) benchmark has primarily been the focus of intense research in visual speech recognition (VSR) during the last few years. As a result, there is an increased risk of overfitting to its excessively used test set, which is only one hour duration. To alleviate this issue, we build a new VSR test set named WildVSR, by closely following the LRS3 dataset creation processes. We then evaluate and analyse the extent to which the current VSR models generalize to the new test data. We evaluate a broad range of publicly available VSR models and find significant drops in performance on our test set, compared to their corresponding LRS3 results. Our results suggest that the increase in word error rates is caused by the models’ inability to generalize to slightly "harder" and in the wild lip sequences than those found in the LRS3 test set. Our new test benchmark is made public in order to enable future research towards more robust VSR models.

Current transformer-based change detection (CD) approaches either employ a pre-trained model trained on large-scale image classification ImageNet dataset or rely on first pre-training on another CD dataset and then fine-tuning on the target benchmark. This current strategy is driven by the fact that transformers typically require a large amount of training data to learn inductive biases, which is insufficient in standard CD datasets due to their small size. We develop an end-to-end CD approach with transformers that is trained from scratch and yet achieves state-of-the-art performance on five benchmarks. Instead of using conventional self-attention that struggles to capture inductive biases when trained from scratch, our architecture utilizes a shuffled sparse-attention operation that focuses on selected sparse informative regions to capture the inherent characteristics of the CD data. Moreover, we introduce a change-enhanced feature fusion (CEFF) module to fuse the features from input image pairs by performing a per-channel re-weighting. Our CEFF module aids in enhancing the relevant semantic changes while suppressing the noisy ones. Extensive experiments on five CD datasets reveal the merits of the proposed contributions, achieving gains as high as 1.35% in intersection over union (IoU) score, compared to the best-published results in the literature. Code is available at https://github.com/mustansarfiaz/ScratchFormer.

Visual Speech Recognition (VSR) differs from the common perception tasks as it requires deeper reasoning over the video sequence, even by human experts. Despite the recent advances in VSR, current approaches rely on labeled data to fully train or finetune their models predicting the target speech. This hinders their ability to generalize well beyond the training set and leads to performance degeneration under out-of-distribution challenging scenarios. Unlike previous works that involve auxiliary losses or complex training procedures and architectures, we propose a simple approach, named Lip2Vec that is based on learning a prior model. Given a robust visual speech encoder, this network maps the encoded latent representations of the lip sequence to their corresponding latents from the audio pair, which are sufficiently invariant for effective text decoding. The generated audio representation is then decoded to text using an off-the-shelf Audio Speech Recognition (ASR) model. The proposed model compares favorably with fully-supervised learning methods on the LRS3 dataset achieving 26 WER. Unlike SoTA approaches, our model keeps a reasonable performance on the VoxCeleb2-en test set. We believe that reprogramming the VSR as an ASR task narrows the performance gap between the two and paves the way for more flexible formulations of lip reading.

We present a method to efficiently generate 3D-aware high-resolution images that are view-consistent across multiple target views. The proposed multiplane neural radiance model, named GMNR, consists of a novel α-guided view-dependent representation (α-VdR) module for learning view-dependent information. The α-VdR module, faciliated by an α-guided pixel sampling technique, computes the view-dependent representation efficiently by learning viewing direction and position coefficients. Moreover, we propose a view-consistency loss to enforce photometric similarity across multiple views. The GMNR model can generate 3D-aware high-resolution images that are view-consistent across multiple camera poses, while maintaining the computational efficiency in terms of both training and inference time. Experiments on three datasets demonstrate the effectiveness of the proposed modules, leading to favorable results in terms of both generation quality and inference time, compared to existing approaches. Our GMNR model generates 3D-aware images of 1024×1024 pixels with 17.6 FPS on a single V100. Code: https://github.com/VIROBO-15/GMNR

Multi-label zero-shot learning strives to classify images into multiple unseen categories for which no data is available during training. The test samples can additionally contain seen categories in the generalized variant. Existing approaches rely on learning either shared or label-specific attention from the seen classes. Nevertheless, computing reliable attention maps for unseen classes during inference in a multi-label setting is still a challenge. In contrast, state-of-the-art single-label generative adversarial network (GAN) based approaches learn to directly synthesize the class-specific visual features from the corresponding class attribute embeddings. However, synthesizing multi-label features from GANs is still unexplored in the context of zero-shot setting. When multiple objects occur jointly in a single image, a critical question is how to effectively fuse multi-class information. In this work, we introduce different fusion approaches at the attribute-level, feature-level and cross-level (across attribute and feature-levels) for synthesizing multi-label features from their corresponding multi-label class embeddings. To the best of our knowledge, our work is the first to tackle the problem of multi-label feature synthesis in the (generalized) zero-shot setting. Our cross-level fusion-based generative approach outperforms the state-of-the-art on three zero-shot benchmarks: NUS-WIDE, Open Images and MS COCO. Furthermore, we show the generalization capabilities of our fusion approach in the zero-shot detection task on MS COCO, achieving favorable performance against existing methods.

Open-world object detection (OWOD) is a challenging computer vision problem, where the task is to detect a known set of object categories while simultaneously identifying unknown objects. Additionally, the model must incrementally learn new classes that become known in the next training episodes. Distinct from standard object detection, the OWOD setting poses significant challenges for generating quality candidate proposals on potentially unknown objects, separating the unknown objects from the background and detecting diverse unknown objects. Here, we introduce a novel end-to-end transformer-based framework, OW-DETR, for open-world object detection. The proposed OW-DETR comprises three dedicated components namely, attention-driven pseudo-labeling, novelty classification and objectness scoring to explicitly address the aforementioned OWOD challenges. Our OW-DETR explicitly encodes multi-scale contextual information, possesses less inductive bias, enables knowledge transfer from known classes to the unknown class and can better discriminate between unknown objects and background. Comprehensive experiments are performed on two benchmarks: MS-COCO and PASCAL VOC. The extensive ablations reveal the merits of our proposed contributions. Further, our model out-performs the recently introduced OWOD approach, ORE, with absolute gains ranging from 1.8% to 3.3% in terms of unknown recall on MS-COCO. In the case of incremental object detection, OW-DETR outperforms the state-of-the-art for all settings on PASCAL VOC. Our code is available at https://github.com/akshitac8/OW-DEtr.

We propose a novel few-shot action recognition framework, STRM, which enhances class-specific feature discrim-inability while simultaneously learning higher-order temporal representations. The focus of our approach is a novel spatio-temporal enrichment module that aggregates spatial and temporal contexts with dedicated local patch-level and global frame-level feature enrichment sub-modules. Local patch-level enrichment captures the appearance-based characteristics of actions. On the other hand, global framelevel enrichment explicitly encodes the broad temporal context, thereby capturing the relevant object features over time. The resulting spatio-temporally enriched representations are then utilized to learn the relational matching between query and support action sub-sequences. We further introduce a query-class similarity classifier on the patch-level enriched features to enhance class-specific feature dis-criminability by reinforcing the feature learning at different stages in the proposed framework. Experiments are performed on four few-shot action recognition benchmarks: Kinetics, SSv2, HMDB51 and UCF101. Our extensive ablation study reveals the benefits of the proposed contributions. Furthermore, our approach sets a new state-of-the-art on all four benchmarks. On the challenging SSv2 benchmark, our approach achieves an absolute gain of 3.5% in classification accuracy, as compared to the best existing method in the literature. Our code and models are available at https://github.com/Anirudh257/strm.

This work proposes a weakly-supervised temporal action localization framework, called D2-Net, which strives to temporally localize actions using video-level supervision. Our main contribution is the introduction of a novel loss formulation, which jointly enhances the discriminability of latent embeddings and robustness of the output temporal class activations with respect to foreground-background noise caused by weak supervision. The proposed formulation comprises a discriminative and a denoising loss term for enhancing temporal action localization. The discriminative term incorporates a classification loss and utilizes a top-down attention mechanism to enhance the separability of latent foreground-background embeddings. The denoising loss term explicitly addresses the foreground-background noise in class activations by simultaneously maximizing intra-video and inter-video mutual information using a bottom-up attention mechanism. As a result, activations in the foreground regions are emphasized whereas those in the background regions are suppressed, thereby leading to more robust predictions. Comprehensive experiments are performed on multiple benchmarks, including THUMOS14 and ActivityNet1.2. Our D2-Net performs favorably in comparison to the existing methods on all datasets, achieving gains as high as 2.3% in terms of mAP at IoU=0.5 on THUMOS14. Source code is available at https://github.com/naraysa/D2-Net.

Multi-label zero-shot learning (ZSL) is a more realistic counter-part of standard single-label ZSL since several objects can co-exist in a natural image. However, the occurrence of multiple objects complicates the reasoning and requires region-specific processing of visual features to preserve their contextual cues. We note that the best existing multi-label ZSL method takes a shared approach towards attending to region features with a common set of attention maps for all the classes. Such shared maps lead to diffused attention, which does not discriminatively focus on relevant locations when the number of classes are large. Moreover, mapping spatially-pooled visual features to the class semantics leads to inter-class feature entanglement, thus hampering the classification. Here, we propose an alternate approach towards region-based discriminability-preserving multi-label zero-shot classification. Our approach maintains the spatial resolution to preserve region-level characteristics and utilizes a bi-level attention module (BiAM) to enrich the features by incorporating both region and scene context information. The enriched region-level features are then mapped to the class semantics and only their class predictions are spatially pooled to obtain image-level predictions, thereby keeping the multi-class features disentangled. Our approach sets a new state of the art on two large-scale multi-label zero-shot benchmarks: NUS-WIDE and Open Images. On NUS-WIDE, our approach achieves an absolute gain of 6.9% mAP for ZSL, compared to the best published results. Source code is available at https://github.com/akshitac8/BiAM.

Generalized zero-shot action recognition is a challenging problem, where the task is to recognize new action categories that are unavailable during the training stage, in addition to the seen action categories. Existing approaches suffer from the inherent bias of the learned classifier towards the seen action categories. As a consequence, unseen category samples are incorrectly classified as belonging to one of the seen action categories. In this paper, we set out to tackle this issue by arguing for a separate treatment of seen and unseen action categories in generalized zero-shot action recognition. We introduce an out-of-distribution detector that determines whether the video features belong to a seen or unseen action category. To train our out-of-distribution detector, video features for unseen action categories are synthesized using generative adversarial networks trained on seen action category features. To the best of our knowledge, we are the first to propose an out-of-distribution detector based GZSL framework for action recognition in videos. Experiments are performed on three action recognition datasets: Olympic Sports, HMDB51 and UCF101. For generalized zero-shot action recognition, our proposed approach outperforms the baseline with absolute gains (in classification accuracy) of 7.0%, 3.4%, and 4.9%, respectively, on these datasets.

Temporal action localization is a challenging computer vision problem with numerous real-world applications. Most existing methods require laborious frame-level supervision to train action localization models. In this work, we propose a framework, called 3C-Net, which only requires video-level supervision (weak supervision) in the form of action category labels and the corresponding count. We introduce a novel formulation to learn discriminative action features with enhanced localization capabilities. Our joint formulation has three terms: a classification term to ensure the separability of learned action features, an adapted multi-label center loss term to enhance the action feature discriminability and a counting loss term to delineate adjacent action sequences, leading to improved localization. Comprehensive experiments are performed on two challenging benchmarks: THUMOS14 and ActivityNet 1.2. Our approach sets a new state-of-the-art for weakly-supervised temporal action localization on both datasets. On the THUMOS14 dataset, the proposed method achieves an absolute gain of 4.6% in terms of mean average precision (mAP), compared to the state-of-the-art. Source code is available at https://github.com/naraysa/3c-net.

An action is typically composed of different parts of the object moving in particular sequences. The presence of different motions (represented as a 1D histogram) has been used in the traditional bag-of-words (BoW) approach for recognizing actions. However the interactions among the motions also form a crucial part of an action. Different object-parts have varying degrees of interactions with the other parts during an action cycle. It is these interactions we want to quantify in order to bring in additional information about the actions. In this paper we propose a causality based approach for quantifying the interactions to aid action classification. Granger causality is used to compute the cause and effect relationships for pairs of motion trajectories of a video. A 2D histogram descriptor for the video is constructed using these pairwise measures. Our proposed method of obtaining pairwise measures for videos is also applicable for large datasets. We have conducted experiments on challenging action recognition databases such as HMDB51 and UCF50 and shown that our causality descriptor helps in encoding additional information regarding the actions and performs on par with the state-of-the art approaches. Due to the complementary nature, a further increase in performance can be observed by combining our approach with state-of-the-art approaches.